- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper focus on how surface-level risk cues affect the safety behavior of LLM. The authors show that making harmful intent more explicit reduces jailbreak success, meanwhile obscuring risk cues can increases vulnerability. A theoretical explanation based on insufficient training coverage and cue-dependent refusal learning during SFT and RLHF. To reduce the risk, the authors propose two methods named PRO and MAX, which use counterfactual data augmentation and worst-case preference optimization to improve safety robustness.
Critical strengths
- Comprehensive main experiments
The experiments cover five open-source LLMs, two benchmarks, and several jailbreak strategies. The results show a broadly consistent pattern across different models and harmful categories.
2.Simple defense strategies
PRO and MAX address the issue through data augmentation and objective modification. Both methods achieve modest improvements without additional inference-time overhead. Even though i think the proposed method have similarity with some exisiting methods.
Critical weaknesses
-
Limited novelty relative to existing work.
The major problem is novelty. The central point of this paper discuss safety-aligned LLM rely on surface-level features rather than underlying harmful intent. While this observation in existing research on safety generalization, shortcut learning, and intent-preserving jailbreak transformations is already well discussed[1,2,3,4,5,6,7]. This part in related work is missing. The proposed PRO and MAX methods also resemble counterfactual data augmentation and worst-case optimization, respectively. The author needs to better discuss existing work and clarify its similarities and differences with it.
-
Insufficient isolation of risk-cue visibility
Although the paper claims to investigate the effect of risk-cue visibility while preserving harmful intent, the explicit and implicit attack settings differ along multiple dimensions beyond cue visibility. Explicit attacks primarily prepend pressure, whereas implicit attacks employ substantially different transformation strategies. These transformations may alter syntactic structure, prompt complexity etc and model behavior. Consequently, the observed differences in attack success cannot be confidently attributed to risk-cue visibility alone. More controlled and ablation experiments are needed.
-
Theoretical analysis does not well-establish the proposed mechanism.
The theoretical analysis provides useful intuition but relies heavily on idealized assumptions. Lemmas 1 and 2 demonstrate that limited training coverage weakens the ability to distinguish intent-aware and cue-reliant refusal rules, but they do not establish that actual LLMs learn such rules during safety alignment. Lemma 3 shows that RL amplifies differences only when the reward function already assigns a greater effective refusal advantage to explicit prompts. For me, this part does not empirically verify this key assumption. The theory is more like a plausible explanation rather than a demonstrated causal account of the observation.
-
The proposed defense methods is not sufficient
The empirical improvements achieved by PRO and MAX are relatively small. For example,MAX reduces implicit attacks ASR from 56.27% to 54.45%, an absolute improvement of only 1.82 percentage points over SafeRLHF-10K. The remaining attack success rate is still substantial.
-
Presentation and experimental organization could be improved.(Minor)
The paper spends too much space on theoretical derivations while leaving the details of PRO and MAX in the appendix. The paper would also benefit from concrete examples and a clearer distinction between theoretical claims and empirical findings.
[1]Wang, Yixu, et al. "Towards Context-Invariant Safety Alignment for Large Language Models."ICML (2026).
[2]Wu, Ping, et al. "Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety." arXiv preprint arXiv:2608.13304 (2026).
[3]Broomfield, Julius, et al. "The structural safety generalization problem." Findings of the Association for Computational Linguistics: ACL 2025. 2025.
[4]Li, Li, et al. "Defenses against prompt attacks learn surface heuristics." Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
[5]Peng, Yu, et al. "Playing language game with llms leads to jailbreaking." arXiv preprint arXiv:2411.12762 (2024).
[6]Li, Jianwei, and Jung-Eun Kim. "Safety alignment can be not superficial with explicit safety signals." ICML (2025).
[7]Ding, Peng, et al. "Friend or Foe: How LLMs’ Safety Mind Gets Fooled by Intent Shift Attack." Transactions of the Association for Computational Linguistics 14 (2026): 2357-2373.
Questions for authors
See weakness
8 comments
Response to Reviewer vXwC [2/4]
Response to Weakness 2 (Controlled visibility). The matched lexical intervention isolates a small change in wording and produces a significant ASR increase in both models. Neutral, label-only, persuasion-only, and wrapper-only controls identify the additional framing and structure effects. The table reports all ten conditions on shared underlying requests.
| Condition | Visibility (1–5) | Judged harmful (n/330) | Qwen3-4B ASR (%) | Qwen3-4B-SafeRL ASR (%) |
|---|---|---|---|---|
| Original request | 4.93 | 309/330 | 5.76 | 4.85 |
| Neutral prefix | 4.91 | 307/330 | 0.30 | 1.21 |
| Risk label only | 4.90 | 307/330 | 0.00 | 2.12 |
| Persuasion only | 4.91 | 306/330 | 2.12 | 3.64 |
| Tempt+Press | 4.90 | 310/330 | 2.12 | 3.03 |
| Minimal euphemistic substitution | 4.03 | 288/330 | 20.00 | 11.82 |
| DrAttack wrapper only | 4.86 | 306/330 | 3.33 | 2.73 |
| FlipAttack wrapper only | 4.90 | 307/330 | 3.33 | 3.03 |
| Full DrAttack | 4.32 | 279/330 | 34.55 | 18.18 |
| Full FlipAttack | 1.01 | 312/330 | 0.00 | 0.00 |
Evaluation and annotation. All ten conditions use 330 shared requests, a single-attempt protocol, and GPT-5.4-mini (6,600 complete scores). Visibility averages use defined ratings on prompts judged harmful. Minimal euphemistic substitution lowers visibility in 182/283 pairs (64.3%); the DrAttack figure is 143/278 (51.4%). The binary harmfulness annotation and the paired visibility ratings are reported separately.
Matched lexical evidence. Minimal euphemistic substitution raises ASR from 5.76% to 20.00% for Qwen3-4B (+14.24 pp; 95% CI [10.30, 18.48]; Holm p = 5.53×10⁻¹⁰) and from 4.85% to 11.82% for Qwen3-4B-SafeRL (+6.97 pp; CI [3.64, 10.61]; Holm p = 0.004), correcting across all 30 model-contrast combinations. The edit changes wording within the original request, adds no attack scaffold or decomposition task, and has median prompt length 1.049 times the original. Among the 283 requests judged harmful in both views, the increases remain +14.84/+8.13 pp (adjusted p < 0.001 for both models). This is direct evidence that a small lexical manipulation can alter safety behavior under matched request and harmfulness conditions.
Contextual framing. Neutral prefixes also lower ASR (0.30%/1.21%) while visibility stays near the original (4.91 versus 4.93), and risk-label prefixes do not differ from them (0.00%/2.12%; paired p = 1.000/0.508); Tempt+Press gives 2.12%/3.03%. Prefixing therefore contributes a framing effect beyond risk wording. The minimal lexical substitution isolates the cue-related component without added context.
Attack structure. DrAttack's wrapper alone yields ASR 3.33%/2.73%, compared with 34.55%/18.18% for the full attack (adjusted paired p < 0.001 in both models). The scaffold-free lexical contrast and the wrapper comparison therefore identify behavioral changes beyond the wrapper alone. Full FlipAttack has visibility 1.01 and zero successes, illustrating the additional role of the particular transformation.
Regression sensitivity. We use the matched lexical comparison as the primary test and regression to assess variation across conditions. With request-clustered standard errors, adjustment for model and log character length gives visibility OR 0.97 [0.91, 1.03] (6,062 observations, 317 requests); adding paragraph count gives 1.11 [1.04, 1.20]. FlipAttack's zero successes cause separation in the full condition-indicator fit. Excluding it gives OR 0.35 [0.29, 0.42], or 0.67 [0.54, 0.83] with condition indicators (5,438 observations, 315 requests). The measured covariates are character length and paragraph count.
Response to Reviewer vXwC [3/4]
Response to Weakness 3 (Theory). The theoretical contribution is a quantitative connection between the stages of safety alignment: finite coverage determines distinguishing evidence, SFT and preference objectives determine corrective loss pressure, and effective reward advantage determines the refusal-logit update under KL regularization. The new experiments measure training-data coverage and policy behavior alongside these formal relations.
Training-data measurement. The existing annotation of 3,000 randomly sampled PKU-SafeRLHF prompts gives:
| Sampled PKU-SafeRLHF training prompts | Low visibility (score ≤ 2) | Lenient threshold (score ≤ 3) |
|---|---|---|
| Harmful prompts (n = 1,960 of 3,000) | 0.6% (11; 95% CI [0.3%, 1.0%]) | 3.7% (95% CI [2.9%, 4.6%]) |
| Harmful prompts with ≥ 1 unsafe response (carry a safety preference signal) | 0.4% (95% CI [0.2%, 0.9%]) | 2.4% (95% CI [1.8%, 3.2%]) |
In this training-data sample, encoding and role-play occur in none of the 1,960 harmful prompts, and task decomposition occurs in two. A paired check of the visibility rubric rates the counterfactual rewrites as less explicit in 41% of pairs and more explicit in 1%. These measurements characterize both the scarcity of the studied transformations and the direction of the rewrite intervention.
The 11 low-visibility harmful prompts among 3,000 sampled prompts give δ ≈ 0.0037. At this value, a 10K-prompt dataset almost surely contains distinguishing examples ((1−δ)^n ≈ e^−37), so the relevant quantity is the corrective pressure in Lemma 2: for ε = 0.05, the risk separation δ·log((1−ε)/ε) is about 0.011 nats, and the local corrective derivative is bounded by δ.
Training intervention. We vary scheduled pair inclusion in the added cost-model objective: 0% trains on original views (orig), 50% uses cf_fraction = 0.5, and 100% uses the PRO checkpoint. The fraction specifies this added objective; δ in the theory describes distinguishing examples in the training distribution. The recipe uses η = 0.25 and seed 42, with the new orig/frac50 logs recording 2,310 CM steps and 93 PPO steps each. All three checkpoints are evaluated on the same 330 requests, attack inputs, and GPT-5.4-mini judge under the Table 2 single-attempt protocol.
| Scheduled pair inclusion | Variant | ASR[E] (%) | ASR[I], DrAttack (%) | Gap (pp) |
|---|---|---|---|---|
| 0% | Original-only extra updates (orig) | 4.85 | 27.88 | 23.03 |
| 50% | frac50 | 5.15 | 29.09 | 23.94 |
| 100% | PRO (mean) | 3.33 | 29.39 | 26.06 |
Paired analysis. We use 100,000 request-level bootstrap resamples, keeping explicit and implicit endpoints together, and exact two-sided McNemar tests for score-5 outcomes. Holm correction covers all six ASR contrasts (three pairs of inclusion settings × two endpoints). The intervals quantify prompt variation conditional on the trained checkpoints and recorded labels.
Transfer through the alignment pipeline. Raising scheduled pair inclusion from 0% to 100% leaves the gap unchanged within uncertainty (+3.03 pp; 95% CI [−1.52, 7.58]); the DrAttack change is +1.52 pp (CI [−2.73, 6.06]; exact p = 0.590, Holm p = 1.000). In the rewrite annotation, 40.6% of counterfactual views are rated less explicit, so the added objective raises low-visibility coverage only partially. The SFT→10K comparison (+22.12 pp; CI [14.85, 29.39]) places the gap increase at the alignment stage.
The training-data sample quantifies scarce coverage, while the SFT→PPO endpoints measure asymmetric alignment gains. Lemma 3 specifies the effective reward ordering under which refusal-logit asymmetry grows. The combined analysis thus identifies the relevant distributional quantity, the training incentive, and the conditional policy response; the controlled interventions examine the effects of changing paired supervision and loss selection.
Response to Reviewer vXwC [1/4]
We thank Reviewer vXwC for the detailed related-work discussion and for recognizing the comprehensive experiments and simplicity of PRO/MAX. We organize the response around the paper's empirical, theoretical, and methodological contributions.
Response to Weakness 1 (Novelty). The paper contributes a connected empirical and training-level account of safety asymmetry: matched prompt experiments identify cue and context effects, the analysis quantifies corrective training pressure, and PRO/MAX intervene on paired preference learning. The comparisons below specify how this contribution relates to prior work [1–7].
(1) Controlled evidence across prompt manipulations and model scales. We compare explicit framing and implicit reformulations of shared underlying requests across eight models from three families. Ten controlled conditions in two models separate lexical changes, prefixes, and attack wrappers. The lexical contrast survives multiplicity correction and a paired harmfulness restriction.
(2) Quantitative connections between training stages. Lemma 1 gives the probability of encountering distinguishing examples; Lemma 2 quantifies population risk separation and local corrective loss pressure. The preference-learning analysis gives the corresponding reward-shift bound, and Lemma 3 derives the reward-conditioned refusal-logit update under KL regularization. These relations give data coverage and the learning objective explicit roles in the correction of cue dependence. Training-data annotation and policy-stage evaluation supply the corresponding measurements.
(3) Paired preference optimization without inference overhead. PRO is a form of counterfactual data augmentation in which views are paired by shared harmful intent and differ in cue visibility. MAX is a per-pair worst-case objective, equivalent to group DRO with two views per group; it directs the pairwise gradient to the worse safety-preference margin. The matched top-k control (response to Reviewer u5Ha, Question 4) tests this pairing against unpaired hard-example selection. AIR [1] anchors optimization on verifiable formats, whereas our paired views vary risk-cue visibility in safety-preference training. WIFA [2] uses shared wrappers on harmful and benign inputs; our benign evaluation measures the resulting policies on XSTest-safe, OR-Bench-Hard, and JBB-benign. The table reports total refusal % with (full / partial) percentages.
Benign behavior alongside safety. PRO lowers XSTest refusal by 5.60 pp relative to 10K (95% CI [−9.60, −2.00]; Holm p = 0.0397 across six benign-set comparisons). MAX has the same aggregate XSTest rate as 10K (24.80%), with OR-Bench/JBB changes of −2.33/+4.00 pp (CIs [−6.33, 1.67]/[−3.00, 11.00]). Together with MAX's held-out ISA-tense and top-k comparisons, these results provide a joint assessment of safety and benign refusal at unchanged inference cost.
We also include the recent ISA attack [7]. On Qwen3.5-4B, 9B, and 27B, its five transformations raise HEx-PHI ASR from at most 0.6% for original requests to 6.1–11.5% (paired McNemar p ≤ 0.007 for every model and transformation), while explicit prompts remain at an ASR floor of at most 0.6%. These results extend the phenomenon to stronger and larger models and complement the controlled comparisons used to analyze its source. The revised Related Work discusses [1–7] directly: structural safety generalization [3], surface heuristics in prompt-attack defenses [4], and language-game jailbreaks [5] motivate testing safety across formulations, while explicit safety signals [6], AIR [1], and WIFA [2] provide complementary training approaches.
References