- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Summary
Authors introduce REFUSALTRACE, a sparse activation-masking jailbreak attack framework based on natural refusal trajectories. It follows the refusal trajectories that the target model naturally generates against the attack prompts as behavioural signals. It works in two steps –
- First, it attributes gate/up projection coordinates near the prompt–response boundary and aggregates candidates through stable voting across trajectories.
- Second, it performs conditional multi-fidelity compression subject to an attack-effectiveness constraint, yielding a compact static mask for inference-time use.
Finally, the outcomes across 11 models: the final masks touch ~0.30% of gate/up coordinates while keeping a 74.9% mean attack success rate and beating the best-performing baseline on 5/6 scenarios.
Critical strengths
Strength
- The core idea is well-motivated and genuinely distinct.
- The ASR definition requires both Llama-Guard-unsafe and non-refused (Equation 5). It rules out the common failure mode of counting degenerate or empty outputs as jailbreaks.
- Evaluation on 11 models is a big plus.
- Authors explicitly highlighted (a) the DeepSeek baseline confound and (b) uneven Qwen2.5-14B compression rather than hiding them.
Critical weaknesses
Weakness
-
All results are given on single runs. Surprisingly, the critical stochastic stage is left uncharacterised, i.e., the method includes a step (Eq. 16) that relies entirely on random sampling, but in the paper the step appears perfectly stable and predictable. The compression search (see Section 3.3) is greedy and path-dependent. Equation 16 samples S restoration contexts, ∆proxy orders which block reach the high-fidelity ASR check, and acceptances (see Equation 17) are order-dependent and never revisited (coarse ---> fine and 64->16->4). It indicates that a different sample yields a different restoration path, a different final mask M*, and likely a different final ASR. If possible, add ≥3 seeds with std. on Table 1 and 2.
-
Average ASR is likely distorted. Models that already have successful jailbreaks 67.4% of the time (see Table 1/DeepSeek-R1-Distil-Llama-8B) heavily skew the macro-average, pool ASR, and final ASR upward. This creates a false impression of universal strength. Intuitively, the core thesis of the paper is that a model’s successful internal refusal trajectories act as the supervision signal. If a model fails to refuse the majority of the time, the extracted refusal signals are expected to be noisy. It means that it cannot be the direct evidence for 'attribution-from-refusals' for a jailbreak.
-
The attribution approximation is not properly examined. The candidate score (in Eq. 10) is a window-averaged first-order term. The gradient x activation with a ReLU retains only positive ones. Two problems can happen: First, (a) first-order sensitivity is a known-poor proxy for a large discrete perturbation (for example, doing zero on the coordinate entirely); the attribution magnitude need not track the effect of actually masking. Second, (b) the ReLU discards coordinates whose first-order product is negative. However, if we do zero them out during joint masking, they might actually be highly effective at breaking the model's safety. By discarding them, you are likely missing out on powerful intervention units. Need more exploration in this direction.
Questions for authors
Kindly consider the 'Weakness' section for further improvements.