Tencent's Zhuque Lab released AI-Infra-Guard on June 30, an open-source framework that reorganizes AI agent red teaming around a structural observation that most existing tools overlook: the attack ...
This research is part of a joint initiative between the Cloud Security Alliance (CSA) and OWASP AI Exchange, building upon the previously published Agentic AI Red Teaming Guide. The objective of this ...
An "agentic threat actor" successfully exploited a Langflow flaw to steal data from a production database server and encrypt ...
11dOpinion
Attorneys Using Evidentiary ChatGPT Transcripts At Trial Are Risking An Unexpected Juror Revolt
Attorneys are using subpoena-obtained AI chat transcripts, such as from ChatGPT, at trial. Jurors though won't necessarily ...
JADEPUFFER is an agentic threat actor (ATA), or an operator whose attack capability is delivered by an AI agent rather than a ...
A curated corpus of real-world security incidents, attack techniques, CVEs, frameworks, and defensive tools for autonomous AI agents. From zero-click Copilot exfiltration to AI-powered C2 channels — ...
2025-06-09 HSF: Defending against Jailbreak Attacks with Hidden State Filtering Cheng Qian et.al. 2409.03788 null 2024-11-29 Conversational Complexity for Assessing Risk in Large Language Models John ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results