Dark Reading·1d ago'Salesbleed' Exploits Salesforce Agents to Enable Slack Phishing#salesbleed#salesforce#slack 6 sources
CyberScoop·2d agoNew bill would create federal investigative body for AI-driven hacks#policy#legislation#ai-agents 4 min
Hacker News · security·2d agoJev Is Not a Language Model, but It Breaks Like One#jev#prompt-injection#typesafe-ai 4 sources 8 min
Dark Reading·2d agoAttackers Manipulate AI Chatbots in Mass Disinformation, Phishing Campaign#ai-security#chatgpt#disinformation 3 sources in the wild
The Register · Security·2d agoGoogle to critical infra orgs: Our AI scanners won't be evil, promise#google#wiz#gemini 2 sources 4 min
Dark Reading·2d agoPrompt-Injection Bug Hits $4B Agentic AI App 'Manus'#manus#prompt-injection#agentic-ai
Help Net Security·2d agoGurucul connects AI activity to identity data for faster threat response#gurucul#siem#uebaTools 6 min
arXiv cs.CR·2d agoThrough Human Eyes and Machine Eyes: Understanding View Mismatch in Video See-Through Extended Reality#extended-reality#meta-quest#prompt-injectionAI safety & security
GBHackers·3d agoCisco Talos Launches CAIRN Tool to Hunt and Track AI-Integrated Malware#ai-security#cisco-talos#llm 13 sources 3 min
arXiv cs.CR·3d agoThe Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning#unlearning#knowledge-editing#tokenizationAI safety & security
TechCrunch · Security·3d agoWhat’s next for cybersecurity, according to Index Ventures’ Shardul Shah#cybersecurity#venture-capital#index-ventures 2 min
arXiv cs.CR·3d agoODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus#object-detection#backdoor#ai-securityAI safety & security
Help Net Security·3d agoPortnox detects and removes unauthorized AI applications from managed devices#ai-policy#ai-security#endpoint-securityTools 3 min
Help Net Security·3d agoBarracuda brings AI security and governance within reach of smaller organizations#ai-security#barracuda#complianceAI industry 3 min
GBHackers·3d agoWeekly Cybersecurity Newsletter – Top 50 Biggest Cybersecurity Stories of the Week#newsletter#roundup#weekly-digest in the wild 11 min
arXiv cs.CR·4d agoExtracting CNNs in the Unknown-Architecture and Feedback-Agnostic Setting#model-extraction#cnn#cryptanalysisAI safety & security
arXiv cs.CR·4d agoA2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem#mcp#agent-security#tool-hijackingAI safety & security
CSO Online·4d ago highZ.ai disables coding assistant feature after flaw exposed enterprise code upload risk#z.ai#zcode#coding-assistant 2 sources 3 min1
Proofpoint Threat Insight·4d agoProofpoint Breaks Down the Divide Between Data Security and AI Security with the Industry’s First Unified Agentic System#proofpoint#ai-security#data-security 2 sources 6 min1
arXiv cs.CR·5d agoEvaluating Coding Agents on Kernel Exploit Generation#kex-bench#coding-agents#kernel-exploitAI safety & security1