Babel is an efficient black-box jailbreaking framework that formalizes sparse safety attention heads via a mathematical obfuscation model and uses iterative distribution refinement to achieve higher attack success rates on models like GPT-4o and Claude-3-5-haiku with around 40 queries.
Mirage in the eyes: Hallucination attack on multi-modal large language models with only attention sink.arXiv preprint arXiv:2501.15269, 1
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ReasoningGuard is an inference-time method that uses attention mechanisms to inject safety aha moments and scaling sampling to defend large reasoning models against jailbreak attacks.
Proposes dynamic token re-weighting during target-domain fine-tuning to mitigate exacerbated attention sink in source-free CDFSL, achieving SOTA on four benchmarks.
citing papers explorer
-
Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
Babel is an efficient black-box jailbreaking framework that formalizes sparse safety attention heads via a mathematical obfuscation model and uses iterative distribution refinement to achieve higher attack success rates on models like GPT-4o and Claude-3-5-haiku with around 40 queries.
-
ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
ReasoningGuard is an inference-time method that uses attention mechanisms to inject safety aha moments and scaling sampling to defend large reasoning models against jailbreak attacks.
-
Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
Proposes dynamic token re-weighting during target-domain fine-tuning to mitigate exacerbated attention sink in source-free CDFSL, achieving SOTA on four benchmarks.
- Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurement