CoTDeceptor:Adversarial Code Obfuscation against CoT-Enhanced LLM Code Agents

LLM-based code agentse.g., ChatGPT Codex are increasingly deployed as detector for code review and security auditing tasks. Although CoT-enhanced LLM vulnerability detectors are believed to provide improved robustness against obfuscated malicious code, we find that their reasoning chains and...

HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models

Large Language Models LLMs remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement; and a Network Traverser for real-time adaptive attack...

Tarallo: Evading Behavioral Malware Detectors in the Problem Space

Machine learning algorithms can effectively classify malware through dynamic behavior but are susceptible to adversarial attacks. Existing attacks, however, often fail to find an effective solution in both the feature and problem spaces. This issue arises from not addressing the intrinsic...

Google Identifies 34 Cracked Versions of Popular Cobalt Strike Hacking Toolkit in the Wild

Google Cloud last week disclosed that it identified 34 different hacked release versions of the Cobalt Strike tool in the wild, the earliest of which shipped in November 2012. The versions, spanning 1.44 to 4.7, add up to a total of 275 unique JAR files, according to findings from the Google Clou...