Involuntary In-Context Learning: Exploiting Few-Shot Pattern Completion to Bypass Safety Alignment in GPT-5.4

Safety alignment in large language models relies on behavioral training that can be overridden when sufficiently strong in-context patterns compete with learned refusal behaviors. We introduce Involuntary In-Context Learning IICL, an attack class that uses abstract operator framing with few-shot...

A Systematic Study of Code Obfuscation against LLM-Based Vulnerability Detection

As large language models LLMs are increasingly adopted for code vulnerability detection, their reliability and robustness across diverse vulnerability types have become a pressing concern. In traditional adversarial settings, code obfuscation has long been used as a general strategy to bypass...

TASO: Jailbreak LLMs Via Alternative Template and Suffix Optimization

Many recent studies showed that LLMs are vulnerable to jailbreak attacks, where an attacker can perturb the input of an LLM to induce it to generate an output for a harmful question. In general, existing jailbreak techniques either optimize a semantic template intended to induce the LLM to produc...

EUVD-2025-6939

Malicious code in bioql PyPI...