Authors show prompt injection attacks that jailbreak LLM paper reviewers for biased acceptance and propose embedding triggers to detect when reviews are LLM-generated rather than human.
Optimization-based prompt injection attack to llm-as-a-judge
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2verdicts
UNVERDICTED 2representative citing papers
Obfuscated prompts exhibit latent embedding collapse onto clean prompt manifolds in BERT encoders, with minimal clean-obfuscated margin of 1.02 and elevated intra-class variance of 3.33 +/- 6.23 despite high detection performance.
citing papers explorer
-
ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected
Authors show prompt injection attacks that jailbreak LLM paper reviewers for biased acceptance and propose embedding triggers to detect when reviews are LLM-generated rather than human.
-
On the Geometric Limits of Transformer Defenses against Obfuscation Attacks: Latent Embedding Collapse & Performance Robustness Gap
Obfuscated prompts exhibit latent embedding collapse onto clean prompt manifolds in BERT encoders, with minimal clean-obfuscated margin of 1.02 and elevated intra-class variance of 3.33 +/- 6.23 despite high detection performance.