AI security
Verified developments, reporting, and emerging signals in ai security.
Enterprise AI Enters Risk Management Phase as Security Concerns Rise
[tl;dr sec] #350 - Reverse Engineer Anything, Tracking AI-integrated Malware, Test-driving Jev
New Aoki Infostealer Targets AI Coding Assistant Credentials
Warning Over High-Risk Vulnerabilities in Widely Used LLM Gateway Tool
Anthropic 'SneakPeek' Flaw Is a Silent Zero-Click Threat
Senators press Trump admin to rally federal government around AI safety, security
Harmonic Security Raises $50 Million for Workforce AI Protection
What You Sign Is Not What You Run: The Verifiability Gap in Quantized LLM Supply Chains
Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation
Kairos: Transactional Security Enforcement at the System Boundary for LLM Agents
CVE-2026-69923 Windows AI Elevation of Privilege Vulnerability
AI Turns Familiar Cyberattacks Into a Race Against Time
Same Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety Classifiers
BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views
Hackers abuse Google Ads, Bing redirects to push Claude ClickFix attacks
AI Models Can Provably Hide Arbitrary Capabilities
OpenAI says it disrupted Russian and Iranian influence ops that used ChatGPT
In Other News: AI Used in Korean Bank Breaches, Poem-Guided Botnet, Empire Admin Gets 40 Years
AI Training Critical as Governance Challenges Grow
Anthropic Fast-Tracks AI Bug Reports to OSS Maintainers, Taps 11 Firms for OT Security
Formula Predicts When AI Chatbots Are at Risk of Turning Bad
[tl;dr sec] #349 - Vulns & Exploits in the AI Era, Package Manager Sandboxing, Testing AI Sandboxes
LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense
Configuring your AI vulnerability harness, Part 2: The steering file
Building your AI vulnerability harness, Part 1
PoeLLM malware infects exposed AI servers in cryptomining attacks
Attackers Hide AI Prompt Injections Inside Phishing Emails
Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
Formal Runtime Verification for Tool-Using LLM Agents: An Offline Same-Benchmark Study on AgentDojo and STAC
Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs
Secure Speculative Decoding for Large Language Models
Fake ChatGPT, Gemini Sites steal advertising accounts, MFA codes
CVE-2026-78501 Microsoft 365 Copilot Business Chat Information Disclosure Vulnerability
The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
South Korea probes bank breaches amid suspected AI-powered attacks
Need for Speed: AI-Driven Attacks Are Changing Security Strategies
Exploitation Hits Rejetto HFS Vulnerability Discovered by AI
Google Suspends Open-Source Bug Bounty Due to AI Vulnerability Reports
Google halts open-source bug bounty program amid AI spam surge
Compromise Is Not Consequence: Evaluating Task-Scoped Authorization in LLM Agents with Paired Replay
Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential
The AI Exposure Brief
A five-minute weekly briefing for CISOs, CIOs, AI governance leaders, and enterprise security teams.
Verified developments. Emerging agent risks. Regulatory changes. Practical control questions.
No spam. Unsubscribe anytime.