Ellipsoid Control is a white-list test-time jailbreak defense that fits an anisotropic ellipsoid from benign activations to constrain projected gradient descent updates, aiming to improve the safety-utility tradeoff over black-list RepE methods.
Intention analysis makes llms a good jailbreak defender
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
dataset 1
method 1
citation-polarity summary
representative citing papers
TwinGate deploys a stateful dual-encoder system with asymmetric contrastive learning to detect decompositional jailbreaks in untraceable LLM traffic at high recall and low false-positive rate with negligible latency.
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.
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.
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.
LLMs fail to detect hidden harmful intent, allowing systematic bypass of safety mechanisms through framing techniques, with reasoning modes often worsening the issue.
citing papers explorer
-
Jailbreak Attacks and Defenses Against Large Language Models: A Survey
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.