Press Ai Security (33 results)

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

Paperback. Condition: new. Paperback. Agentic AI Security: Protecting Autonomous Agents, AI Workflows, and Intelligent Systems in the EnterpriseYour organisation is deploying AI agents that plan, remember, call APIs, and act across your systems. That shift drives faster operations, but it expands your attack surface beyond traditional application security. One compromised prompt, poisoned document, or over-privileged tool call can turn an agent into a pathway for data theft, fraud, or systemic disruption.Agentic AI Security is a practical, enterprise-ready book to deploy agents with confidence capturing the value of agentic AI without betting reputation, compliance, or customer trust on ad hoc controls.What you will be able to do after reading this bookDeploy agents safely at scale. Map risks across single-agent, multi-agent, and workflow architectures and design controls that match real production behavior.Defend against agent-specific attacks. Recognise and mitigate prompt injection (direct and indirect), tool abuse and tool poisoning, memory manipulation, multi-agent impersonation, and cross-session data leakage before they become incidents.Threat-model agent systems with confidence. Apply trust-boundary analysis, STRIDE, and MITRE ATLAS to agentic AI, and walk through a complete threat-modeling example you can reuse on your own projects.Lock down identity, access, and secrets. Establish agent identities, enforce least privilege, manage API keys and tokens, and implement authorisation policies that keep autonomy from becoming uncontrolled privilege.Protect memory, RAG, and knowledge stores. Secure short and long-term agent memory, vector databases, and retrieval-augmented generation pipelines against poisoning, unauthorised retrieval, and governance failures.Harden tools, APIs, and integrations. Control tool invocation boundaries, validate API usage, manage third-party risk, implement human in the loop approvals for high-impact actions, and prepare for emerging protocols such as MCP.Operate with governance. Build AI governance for agents, instrument logging and monitoring, detect abuse through behavioral analytics, and run incident response tailored to autonomous systems.Stay audit-ready. Map your program to ISO 42001, the NIST AI Risk Management Framework, the EU AI Act, and industry-specific requirements.Stand up a durable security program. Apply security-by-design, shift-left practices, secure SDLC integration, assessments, penetration testing, and clear ownership across security, engineering, and risk. Who this book is forLeaders, security architects, CISOs, security engineers, AI engineers, enterprise architects, governance and risk professionals, and technical leaders who must enable agentic AI in production not block it and need a shared language and concrete controls to do it responsibly.What's insideNine focused chapters cover architectures, threats, threat modeling, identity and access, memory and RAG, tools and APIs, governance and incident response, and program design.If your enterprise is moving from pilots to production agents in customer support, SecOps, software delivery, HR, finance, or business process automation this book helps you turn autonomy into a managed capability: observable, auditable, constrained, and defensible.Stop treating agents like smarter chatbots. Start securing them like strategic digital employees with the controls your business actually needs. This book includes a free bonus book and free online AI security course. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.…

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

Paperback. Condition: new. Paperback. AI Security and SBOM: Securing the AI Software Supply Chain A Practical Guide to Software Bills of Materials, AI Model Transparency, and Supply Chain Risk Management Your AI solutions depend on far more than application code. Models, datasets, training pipelines, fine-tuning jobs, vector indexes, third-party APIs, and cloud-hosted services all shape what your AI does and what can go wrong. Traditional Software Bills of Materials (SBOMs) were built for conventional software. They were never designed for this expanded, opaque AI supply chain. This book gives you a practical path from SBOM fundamentals to a working AI supply chain security program so you can see what you have, trust what you deploy, and respond when something breaks. What you will be able to do after reading this book Build complete visibility into your AI stack: Inventory models, datasets, pipelines, frameworks, and third-party dependencies, not just libraries and containersExtend SBOM concepts into AI-BOM, Model BOM (MBOM), Dataset BOM (DBOM), and Pipeline BOM (PBOM)Map hidden relationships across training, fine-tuning, evaluation, and inferenceReduce real supply chain risk before it reaches production: Identify and prioritise threats including model poisoning, data poisoning, malicious pre-trained models, artefact tampering, and dependency compromiseAssess risks from open-source ML libraries, model repositories, containers, and API providersValidate dataset integrity, track model lineage, and confirm the artefact you tested is the artefact you deployedOperationalise AI supply chain security in your organisation: Design an AI BOM framework with clear scope, asset classification, governance roles, and ownershipAutomate asset discovery and generate AI-aware SBOMs using standards like CycloneDX ML extensionsIntegrate inventory, validation, and policy enforcement into CI/CD, MLOps, and DevSecOps workflowsMeet regulatory and audit expectations with evidence, rather than guesswork: Align your program with Executive Order 14110, the EU AI Act, NIST AI RMF, and Secure by Design initiativesManage AI vendor risk with SBOM procurement clauses, model assurance reviews, and continuous third-party monitoringCollect audit ready evidence, map controls, and report supply chain posture to leadership and the boardDetect, contain, and recover from AI supply chain incidents: Monitor for drift, artefact integrity failures, and behavioural anomalies at runtimeRespond to compromised models, poisoned datasets, and pipeline tampering with structured forensics and rebuild proceduresMeasure success with coverage metrics, risk reduction indicators, compliance readiness, and business valueWho this book is for Written for security professionals, leaders, architects, DevSecOps engineers, AI/MLOps practitioners, risk and compliance teams, and technology leaders who need actionable guidance. Whether you are launching a pilot program or scaling AI SBOM across the enterprise, you will find frameworks, automation strategies, rollout plans, and KPIs you can apply immediately. AI supply chain failures rarely look like traditional breaches. A backdoor into a model can behave normally until a specific trigger appears. Poisoned training data can produce subtle, dangerous outputs while your application code remains untouched. Without provenance, inventory, and integrity controls, you cannot know what your AI was built from or whether it changed after approval. Stop guessing about your AI dependencies. Start building the visibility, controls, and confidence your organisation needs to ship AI responsibly. Incl Shipping may be from multiple locations in the US or from the UK, depending on stock availability.…

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

Paperback. Condition: new. Paperback. Security teams adopted agentic AI with justified urgency. Alert volumes outpace analyst capacity. Vulnerability backlogs grow faster than remediation cycles. Compliance evidence demands continuous collection, not quarterly scrambles. Autonomous agents promised to close those gaps by triaging alerts, enriching incidents, and drafting response actions at machine speed.The early wins were tangible, mean time to triage dropped. Enrichment that once required thirty minutes now completes in seconds. However a second invoice arrived alongside the operational gains token bills, compute surges, orchestration platform fees, and integration costs that no one fully forecasted during the pilot. Agentic security pipelines are consumption engines. Every alert entering an LLM-powered triage workflow consumes input tokens. Every enrichment step adds per-request API fees. Every orchestration hop between SIEM, SOAR, vulnerability management, and ticketing platforms accrues compute and data transfer charges. This book is for security analysts, vulnerability managers, compliance officers, IT managers, and CISOs who need to govern agentic AI spend without sacrificing response times. Cost discipline and operational speed are not opposing goals they become opposing goals only when teams treat agentic AI as an open-ended experiment rather than a governed production service. Uncontrolled spend erodes return on investment predictably. It inflates the denominator of every security efficiency metric and triggers budget clawbacks when scale would deliver the greatest risk reduction. Ungoverned cost cutting degrades outcomes through shrunk context windows, cheapest-model routing that floods analysts with false positives, and disabled enrichment that misses critical correlations. Boards and CFOs will fund programs that deliver measurable risk reduction within forecasted spend envelopes not programs that behave like utility bills with no thermostat. Agentic security costs fall into three overlapping categories token spend for LLM inference across detection, triage, enrichment, and response drafting; compute spend for infrastructure running agents and processing event streams; and orchestration spend for workflow engines, message queues, API gateways, third-party licenses, and data egress. Effective FinOps treats these three categories as a system. Chapters move from cost anatomy to governed scale. You will decompose pipeline spend by workflow and lifecycle stage. You will calculate unit economics cost per alert, cost per incident, cost per remediated vulnerability and use those metrics in funding conversations with finance and executive leadership. You will forecast monthly token demand by workflow, severity tier, and business unit, then implement guardrails including rate limits, caching, context compression, and fallback models that preserve investigative quality. You will right-size compute for burst versus steady-state workloads, compare SaaS, dedicated, and hybrid deployment models, and apply autoscaling and spend caps that protect response SLAs during incidents. Orchestration and governance chapters address redundant agent elimination, integration fee management, FinOps dashboards, chargeback accountability, and continuous improvement cycles. The conclusion provides a phased adoption checklist from baseline measurement through governed scale. Measure before you optimize. Tier consumption by risk. Design for burst, not average Tuesdays. Report outcomes with dollars. Disciplined FinOps turns agentic security from a cost risk into a durable operational advantage faster response, clearer accountability, and executive trust that survives the first unexpected invoice.Includes free bonus book and free online AI security course. Includes mock finops for AI security dashboard. Thi Shipping may be from multiple locations in the US or from the UK, depending on stock availability.…

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

Paperback. Condition: New.

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

PAP. Condition: New. New Book. Shipped from UK. Established seller since 2000.

Taschenbuch. Condition: Neu. Neuware.

Taschenbuch. Condition: Neu. Neuware - Resilient Infrastructure for Security treats resilience and security as one design problem, how to build, operate, and recover infrastructure so that compromise, failure, and change do not become catastrophe. Written for security engineers, site reliability engineers, platform and infrastructure engineers, architects, and the technical leaders who own those systems, the book gives you a working model and the patterns to apply it. Identity, network trust boundaries, compute and change, data and secrets, and observability are treated as pillars that must survive stress. Detection, incident response, clean recovery, continuous assurance, and supply-chain dependency are treated as engineered capability. Later chapters cover platform paved roads, decision-making under trade-offs, and a 90-day and 12-month roadmap. The patterns are portable across cloud, hybrid, and on-premises estates. You do not need a particular vendor, compliance regime, or tool stack. Where NIST, ISO, and CIS appear, they are maps, not the work itself. The aim is practical, a smaller blast radius, a cleaner restore, and faster learning, so the next stressful day is survivable.…

Taschenbuch. Condition: Neu. Neuware - Enterprise AI is scaling faster than most security programs can prove they are working. Boards, regulators, and auditors increasingly ask the same question: How do you know your AI is secure and how do you demonstrate it Most AI security guidance stops at controls, threat models, or governance frameworks. AI Security Metrics & KPIs fills the gap with a practical measurement playbook: what to measure, how to define KPIs and key risk indicators (KRIs), and how to report results to executives, risk committees, and the board.Written for CISOs, AI governance leaders, risk managers, security architects, internal auditors, compliance teams, and executive leadership, this book translates AI security into metrics that drive decisions not vanity dashboards. You will learn how to distinguish security metrics from governance metrics, why traditional security KPIs fall short for AI, and how to build a measurement strategy with clear objectives, scope, and accountability.Inside you will learn how to: - Design governance metrics for program oversight, policy compliance, AI asset inventory, third-party AI risk, and executive dashboards- Quantify AI risk with scoring models, KRIs for high-risk models and critical use cases, residual risk measurement, and enterprise risk reporting- Measure secure AI development: SDLC adoption, testing coverage, red-team outcomes, model assessments, and DevSecOps pipeline controls- Track model security: exposure, prompt injection, abuse, adversarial attacks, integrity and drift, and model resilience scorecards- Protect data and privacy for AI: classification, leakage, training-data provenance, RAG security, and regulatory compliance indicators- Govern agentic AI: agent inventory, activity and tool usage, identity and access, workflow approvals, and multi-agent trust monitoring- Benchmark maturity across governance, technical security, and operations and improve continuously- Deliver board-ready reporting: executive dashboards, top KPIs, enterprise scorecards, and evidence for regulators and auditors- Stand up an AI security measurement program: success criteria, metric selection, automation via SIEM and governance platforms, and ongoing optimisationThe book aligns with real-world programs built on NIST AI RMF, ISO 42001, the EU AI Act, MITRE ATLAS, and enterprise AI governance without replacing those frameworks. It shows you how to operationalise them with indicators leadership can trust.If your AI investments are growing but your assurance story is not, this is the reference to move from we have controls to we can measure, manage, and report AI security effectively. Includes free bonus book and free online AI security course.The book gives access to a mock dashboard demonstrating AI security metrics and KPI in a working environment.…

Condition: New. Print on Demand.

Paperback. Condition: new. Paperback. Your vulnerability scanner found another ten thousand issues last quarter. Your ticketing system created assignments. Your patch platform scheduled maintenance windows. And yet the backlog grew, critical findings aged past their SLA, and your compliance team spent three weeks assembling evidence for an audit that captured posture from sixty days earlier.This is the paradox of modern vulnerability management. Organizations have invested heavily in detection and workflow tools, but the gap between finding and closure and between remediation and provable compliance remains stubbornly wide. Security analysts drown in duplicate alerts. Vulnerability managers negotiate priorities instead of reducing exposure. IT managers receive tickets missing the context needed to act. Compliance officers reconcile conflicting exports from systems never designed to speak the same language. The root cause is not lack of effort, it is lack of connected automation that adapts when context changes.Rules-based automation and SOAR playbooks execute fixed sequences. They work for repeatable steps but break when judgment is required. When a new exploit drops, a critical asset moves subnets, or a compensating control expires, rigid playbooks do not adapt. Agentic AI introduces autonomous agents that reason over live data, select tools, pursue goals, and revise plans when conditions shift. A self-healing security pipeline chains these agents across the vulnerability lifecycle prioritizing findings using risk context beyond raw CVSS scores, orchestrating remediation through tickets, patch schedules, and compensating controls, verifying closure with automated rescans, and reporting compliance status continuously from pipeline data rather than manual exports. Humans focus on exceptions, policy decisions, and high-impact tradeoffs while agents handle repetitive coordination. Approval gates, guardrails, and audit trails keep autonomy accountable. This book is for security analysts, vulnerability managers, compliance officers, and IT managers who share responsibility for reducing exposure and proving control effectiveness. You do not need a machine learning background. You need a clear architecture and operational playbook you can adapt to your environment. Chapters move from concepts to implementation. You will map agentic AI onto the discover, prioritize, remediate, verify, and report phases of vulnerability management. You will design pipeline architecture with ingestion, prioritization, remediation orchestration, and compliance reporting layers, integrating scanners, CMDBs, ticketing systems, patch tools, and GRC platforms with guardrails and human-in-the-loop approval gates. Prioritization chapters address risk-based scoring combining CVSS, exploitability, asset criticality, and threat intelligence, with multi-agent triage for deduplication, false positive reduction, and SLA-based routing. Remediation chapters orchestrate patch deployment, ticket creation, and change management handoffs within green, yellow, and red approval zones, defining safe boundaries, compensating controls, and rollback procedures across hybrid environments. Compliance chapters map findings and remediation status to SOC 2, ISO 27001, PCI DSS, and CIS Controls, auto-generating evidence packages and executive reports from live pipeline data instead of quarterly snapshots. The final chapter addresses phased rollout, success metrics, ROI models, and governance, with a thirty-day roadmap for piloting your first autonomous vulnerability workflow. Your vulnerability backlog is not a permanent condition. Self-healing security pipelines make continuous improvement the default operating mode closing findings, proving remediation, and freeing your team to focus on the judgment calls that only humans should make.<b Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Paperback. Condition: new. Paperback. AI Security and SBOM: Securing the AI Software Supply Chain A Practical Guide to Software Bills of Materials, AI Model Transparency, and Supply Chain Risk Management Your AI solutions depend on far more than application code. Models, datasets, training pipelines, fine-tuning jobs, vector indexes, third-party APIs, and cloud-hosted services all shape what your AI does and what can go wrong. Traditional Software Bills of Materials (SBOMs) were built for conventional software. They were never designed for this expanded, opaque AI supply chain. This book gives you a practical path from SBOM fundamentals to a working AI supply chain security program so you can see what you have, trust what you deploy, and respond when something breaks. What you will be able to do after reading this book Build complete visibility into your AI stack: Inventory models, datasets, pipelines, frameworks, and third-party dependencies, not just libraries and containersExtend SBOM concepts into AI-BOM, Model BOM (MBOM), Dataset BOM (DBOM), and Pipeline BOM (PBOM)Map hidden relationships across training, fine-tuning, evaluation, and inferenceReduce real supply chain risk before it reaches production: Identify and prioritise threats including model poisoning, data poisoning, malicious pre-trained models, artefact tampering, and dependency compromiseAssess risks from open-source ML libraries, model repositories, containers, and API providersValidate dataset integrity, track model lineage, and confirm the artefact you tested is the artefact you deployedOperationalise AI supply chain security in your organisation: Design an AI BOM framework with clear scope, asset classification, governance roles, and ownershipAutomate asset discovery and generate AI-aware SBOMs using standards like CycloneDX ML extensionsIntegrate inventory, validation, and policy enforcement into CI/CD, MLOps, and DevSecOps workflowsMeet regulatory and audit expectations with evidence, rather than guesswork: Align your program with Executive Order 14110, the EU AI Act, NIST AI RMF, and Secure by Design initiativesManage AI vendor risk with SBOM procurement clauses, model assurance reviews, and continuous third-party monitoringCollect audit ready evidence, map controls, and report supply chain posture to leadership and the boardDetect, contain, and recover from AI supply chain incidents: Monitor for drift, artefact integrity failures, and behavioural anomalies at runtimeRespond to compromised models, poisoned datasets, and pipeline tampering with structured forensics and rebuild proceduresMeasure success with coverage metrics, risk reduction indicators, compliance readiness, and business valueWho this book is for Written for security professionals, leaders, architects, DevSecOps engineers, AI/MLOps practitioners, risk and compliance teams, and technology leaders who need actionable guidance. Whether you are launching a pilot program or scaling AI SBOM across the enterprise, you will find frameworks, automation strategies, rollout plans, and KPIs you can apply immediately. AI supply chain failures rarely look like traditional breaches. A backdoor into a model can behave normally until a specific trigger appears. Poisoned training data can produce subtle, dangerous outputs while your application code remains untouched. Without provenance, inventory, and integrity controls, you cannot know what your AI was built from or whether it changed after approval. Stop guessing about your AI dependencies. Start building the visibility, controls, and confidence your organisation needs to ship AI responsibly.</ Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Paperback. Condition: new. Paperback. Security teams adopted agentic AI with justified urgency. Alert volumes outpace analyst capacity. Vulnerability backlogs grow faster than remediation cycles. Compliance evidence demands continuous collection, not quarterly scrambles. Autonomous agents promised to close those gaps by triaging alerts, enriching incidents, and drafting response actions at machine speed.The early wins were tangible, mean time to triage dropped. Enrichment that once required thirty minutes now completes in seconds. However a second invoice arrived alongside the operational gains token bills, compute surges, orchestration platform fees, and integration costs that no one fully forecasted during the pilot. Agentic security pipelines are consumption engines. Every alert entering an LLM-powered triage workflow consumes input tokens. Every enrichment step adds per-request API fees. Every orchestration hop between SIEM, SOAR, vulnerability management, and ticketing platforms accrues compute and data transfer charges. This book is for security analysts, vulnerability managers, compliance officers, IT managers, and CISOs who need to govern agentic AI spend without sacrificing response times. Cost discipline and operational speed are not opposing goals they become opposing goals only when teams treat agentic AI as an open-ended experiment rather than a governed production service. Uncontrolled spend erodes return on investment predictably. It inflates the denominator of every security efficiency metric and triggers budget clawbacks when scale would deliver the greatest risk reduction. Ungoverned cost cutting degrades outcomes through shrunk context windows, cheapest-model routing that floods analysts with false positives, and disabled enrichment that misses critical correlations. Boards and CFOs will fund programs that deliver measurable risk reduction within forecasted spend envelopes not programs that behave like utility bills with no thermostat. Agentic security costs fall into three overlapping categories token spend for LLM inference across detection, triage, enrichment, and response drafting; compute spend for infrastructure running agents and processing event streams; and orchestration spend for workflow engines, message queues, API gateways, third-party licenses, and data egress. Effective FinOps treats these three categories as a system. Chapters move from cost anatomy to governed scale. You will decompose pipeline spend by workflow and lifecycle stage. You will calculate unit economics cost per alert, cost per incident, cost per remediated vulnerability and use those metrics in funding conversations with finance and executive leadership. You will forecast monthly token demand by workflow, severity tier, and business unit, then implement guardrails including rate limits, caching, context compression, and fallback models that preserve investigative quality. You will right-size compute for burst versus steady-state workloads, compare SaaS, dedicated, and hybrid deployment models, and apply autoscaling and spend caps that protect response SLAs during incidents. Orchestration and governance chapters address redundant agent elimination, integration fee management, FinOps dashboards, chargeback accountability, and continuous improvement cycles. The conclusion provides a phased adoption checklist from baseline measurement through governed scale. Measure before you optimize. Tier consumption by risk. Design for burst, not average Tuesdays. Report outcomes with dollars. Disciplined FinOps turns agentic security from a cost risk into a durable operational advantage faster response, clearer accountability, and executive trust that survives the first unexpected invoice.Includes free bonus book and free online AI security course. Includes mock finops for AI security dashboard Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…

Condition: New. Print on Demand.

Paperback. Condition: new. Paperback. Enterprise AI is scaling faster than most security programs can prove they are working. Boards, regulators, and auditors increasingly ask the same question: How do you know your AI is secure and how do you demonstrate it? Most AI security guidance stops at controls, threat models, or governance frameworks. AI Security Metrics & KPIs fills the gap with a practical measurement playbook: what to measure, how to define KPIs and key risk indicators (KRIs), and how to report results to executives, risk committees, and the board.Written for CISOs, AI governance leaders, risk managers, security architects, internal auditors, compliance teams, and executive leadership, this book translates AI security into metrics that drive decisions not vanity dashboards. You will learn how to distinguish security metrics from governance metrics, why traditional security KPIs fall short for AI, and how to build a measurement strategy with clear objectives, scope, and accountability.Inside you will learn how to: Design governance metrics for program oversight, policy compliance, AI asset inventory, third-party AI risk, and executive dashboardsQuantify AI risk with scoring models, KRIs for high-risk models and critical use cases, residual risk measurement, and enterprise risk reportingMeasure secure AI development: SDLC adoption, testing coverage, red-team outcomes, model assessments, and DevSecOps pipeline controlsTrack model security: exposure, prompt injection, abuse, adversarial attacks, integrity and drift, and model resilience scorecardsProtect data and privacy for AI: classification, leakage, training-data provenance, RAG security, and regulatory compliance indicatorsGovern agentic AI: agent inventory, activity and tool usage, identity and access, workflow approvals, and multi-agent trust monitoringBenchmark maturity across governance, technical security, and operations and improve continuouslyDeliver board-ready reporting: executive dashboards, top KPIs, enterprise scorecards, and evidence for regulators and auditorsStand up an AI security measurement program: success criteria, metric selection, automation via SIEM and governance platforms, and ongoing optimisationThe book aligns with real-world programs built on NIST AI RMF, ISO 42001, the EU AI Act, MITRE ATLAS, and enterprise AI governance without replacing those frameworks. It shows you how to operationalise them with indicators leadership can trust.If your AI investments are growing but your assurance story is not, this is the reference to move from we have controls to we can measure, manage, and report AI security effectively. Includes free bonus book and free online AI security course.The book gives access to a mock dashboard demonstrating AI security metrics and KPI in a working environment. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.…

Condition: New. Print on Demand.

Condition: New. Print on Demand.

Condition: New. Print on Demand.

Condition: New. Print on Demand.

Paperback. Condition: New.