How Reliable Are AI Attackers against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency

Large language models LLMs can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated trials remains unstudied. This work presents the first large-scale empirical measurement of LLM attack consistency: 400 autonomous penetration testing runs...

When Safety Detectors Aren'T Enough: a Stealthy and Effective Jailbreak Attack on LLMs Via Steganographic Techniques

Jailbreak attacks pose a serious threat to large language models LLMs by bypassing built-in safety mechanisms and leading to harmful outputs. Studying these attacks is crucial for identifying vulnerabilities and improving model security. This paper presents a systematic survey of jailbreak method...

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-Based Multi-Agent Debate

Multi-Agent Debate MAD, leveraging collaborative interactions among Large Language Models LLMs, aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing characteristics, particularly susceptibility to jailbreak attack...

The vulnerability in the web interface for managing microprogrammed software routers of Cisco Small Business RV340, RV340W, RV345, and RV345P allows a perpetrator to execute arbitrary commands.

The vulnerability of the web-based management interface for Cisco Small Business RV340, RV340W, RV345, and RV345P routers exists due to the lack of measures taken to neutralize special elements used in the operating system commands. Exploiting this vulnerability allows a malicious actor to execut...