concept
active
concept:backdoor-attacks

Backdoor attacks

Hidden triggers that elicit malicious behavior.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Sleeper agent
    associated_with
    Model trained to behave harmlessly but later exhibits harmful behavior; features may reveal such hidden objectives.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Backdoor in codeconcept0.816
    Feature detecting mentions of backdoors and hidden malicious functionality.
  • Jailbreak Attackconcept0.773
    Security attack that bypasses LLM safety alignment by suppressing deliberation or exploiting reflection inhibition.
  • Backtrackingconcept0.724
    Reasoning behavior for which the SAEs learned features.
  • Prefill Attackmethod0.723
    Adversarial multi-turn experiment where first turn uses pre-finetuning model to test if follow-up maintains character
  • Pre-fill attackconcept0.711
    Putting words in the target model's mouth to elicit behavior.
  • Back-propagationmethod0.706
    Standard learning algorithm for deep neural networks that propagates error signals to adjust weights; lacks convergence guarantee for non-linearly separable functions
  • SAE latents that rise as correction approaches and peak after self-correction begins, complementing OTDs
  • Optimization-based jailbreak method appending strings to prompts to elicit harmful outputs.