MM-SafetyBench
PulseAugur coverage of MM-SafetyBench — every cluster mentioning MM-SafetyBench across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New SPARK framework enhances VLM safety by repairing KV memory
Researchers have developed SPARK, a novel framework designed to enhance the safety of vision-language models (VLMs) by addressing vulnerabilities in their multimodal key-value (KV) memory. This two-stage approach identi…
-
New CASA method boosts multimodal LLM safety alignment
Researchers have developed CASA (Classification Augmented with Safety Attention), a novel strategy to enhance the safety alignment of multimodal large-language models (MLLMs). CASA uses internal MLLM representations to …
-
New 'Furina' Attack Exploits LLM Safety Instability
Researchers have developed a new attack method called Furina that exploits instability in the safety alignment of large language models. This attack capitalizes on a phenomenon where small input changes can lead to unpr…