Jointly training an Attacker and Defender LLM in a non-zero-sum game with pairwise preference judges produces a defender with much lower jailbreak success while preserving general utility.
Strategic Deflection: Defending LLMs from Logit Manipulation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level attacks have demonstrated the ability to bypass these safeguards by directly manipulating the token-selection process during generation. We introduce Strategic Deflection (SDeflection), a defense that redefines the LLM's response to such advanced attacks. Instead of outright refusal, the model produces an answer that is semantically adjacent to the user's request yet strips away the harmful intent, thereby neutralizing the attacker's harmful intent. Our experiments demonstrate that SDeflection significantly lowers Attack Success Rate (ASR) while maintaining model performance on benign queries. This work presents a critical shift in defensive strategies, moving from simple refusal to strategic content redirection to neutralize advanced threats.
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Safety Alignment of LMs via Non-cooperative Games
Jointly training an Attacker and Defender LLM in a non-zero-sum game with pairwise preference judges produces a defender with much lower jailbreak success while preserving general utility.