Jailbreak Attacks
PulseAugur coverage of Jailbreak Attacks — every cluster mentioning Jailbreak Attacks across labs, papers, and developer communities, ranked by signal.
-
New framework uses computation graphs to diagnose LLM jailbreak vulnerabilities
Researchers have developed a new framework to understand how large language models (LLMs) are vulnerable to adversarial prompts and jailbreak attacks. This method uses paired internal computation graphs to represent pro…
-
New research explores multimodal and sparse autoencoder methods to combat LLM jailbreaks
Researchers are developing new methods to combat jailbreaking attacks on spoken language models (SLMs). One approach, JAMA, uses a joint multimodal optimization framework to simultaneously attack both audio and text mod…
-
New safeguard uses draft models to detect LLM jailbreaks
Researchers have developed a new safeguard to improve the safety of large language models (LLMs) against jailbreak attacks. This system leverages the transferability of attacks from larger models to smaller "draft" mode…
-
New research tackles LLM jailbreaks with dynamic evaluation and robust defense strategies
Multiple research papers explore advanced techniques for enhancing the safety and robustness of large language models (LLMs) against jailbreak attacks. These studies introduce novel frameworks and methods for evaluating…