LIRA aligns latent instruction representations in LLMs to defend against jailbreaks, backdoors, and undesired knowledge, blocking over 99% of PEZ attacks and achieving optimal WMDP forgetting.
Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs
LIRA aligns latent instruction representations in LLMs to defend against jailbreaks, backdoors, and undesired knowledge, blocking over 99% of PEZ attacks and achieving optimal WMDP forgetting.