Greedy random search recovers token sequences that elicit harmful response prefixes from LLMs without meaningful instructions, showing natural backdoors are present yet require more effort than semantic attacks.
blue" data (harmful questions with safe/refusal responses) and
6 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
6
Pith papers citing it
2
external citations · external index
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 2polarities
background 2representative citing papers
Task-preserving perturbations of correct exemplars can degrade ICL performance by changing the effective evidence mixture used for inference.
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.
Personalization through long-term memory in LLM agents increases harmful query success rates by 15.8-243.7% via intent legitimation, measured on the new PS-Bench benchmark across frameworks.
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
citing papers explorer
-
On the Hardness of Junking LLMs
Greedy random search recovers token sequences that elicit harmful response prefixes from LLMs without meaningful instructions, showing natural backdoors are present yet require more effort than semantic attacks.
-
When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
Task-preserving perturbations of correct exemplars can degrade ICL performance by changing the effective evidence mixture used for inference.
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
-
When AI reviews science: Can we trust the referee?
AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.
-
When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
Personalization through long-term memory in LLM agents increases harmful query success rates by 15.8-243.7% via intent legitimation, measured on the new PS-Bench benchmark across frameworks.
-
Towards an AI co-scientist
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.