- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies adversarial-suffix jailbreaks against LLM agents. It connects two existing ways of framing the attack objective, the first being the REINFORCE style objective over possible inputs, and the second being the GCG style optimization objective of maximizing the log likelihood of the harmful response by combining them to sample from a distribution in which responses have high weight if they are likely to be sampled by the model and also harmful. The authors develop a practical algorithm for sampling from this distirbution called OPUR.This outperforms the prior baseline by 13.07% on AgentHarm and similar gains on WebShop and InjecAgent.
Critical strengths
-
The link between the two kinds of objectives as effectively two different paradigms for LLM jailbreaking is very interesting and the theoretical derivation is nice. It also explains a known failure of REINFORCE-style attacks as early in optimization nearly all samples are benign so the gradient is near 0 and reweighting toward likely and harmful responses addresses exactly that.
-
Agent rollouts are stochastic, so a deterministic attack that places targets using a single rollout, as UDora does, can overfit to one trajectory. OPUR instead aggregates several rollouts and samples insertion positions, which introduces stochasticity into the objective to prevent overfitting to any one kind of objective.
Critical weaknesses
-
I'm not sure how relevant the theory is to the actual method. The theory uses fairly standard techniques from reward weighted regression and expectation maximization, but the algorithm itself doesn't really use the method at all. The paper says its a practical realization of sampling targets from that distribution of both likely and harmful responses, but OPUR never defines the harmful distribution, or attempts to somehow actually estimate this likely and harmful response distribution. Instead it uses the splicing technique to insert jailbreaks and then uses UDora's loss function, which raises the question of the actual novelty of the approach beyond the theory.
-
There are no seed values to justify the statistical significance of the results.
Questions for authors
- What is the per-step and total compute (forward/backward passes, wall-clock) of OPUR versus UDora and other baselines?
- How does softmax position sampling relate with greedy top scoring or random selection?
- Is there any actual link between the theory and the algorithm? Where does OPUR actually sample from this likely and harmful response distribution, and how is it actually constructed practically.
3 comments
Official Comment by Reviewer 5Rju
Thank you for the response and the new experiments. My main concern remains the link between the theory and the algorithm. The revised text now describes OPUR as a practical surrogate for which the theory provides only a design rationale, with its effectiveness supported by attack performance. This is fine, but I think that the paper needs to be structured differently because a large majority of the paper is deriving this.
The rollout comparison is nice, and does show that more compute does lead to better ASR. Ideally I would have liked to see a matched compute vs ASR plot for all the methods, but the results show that there is still a gain at roughly the same compute, so I think this is fine. If the authors restructure the first part of the paper to talk less about the theory and more about the fundamental way the algorithm works, I will increase my score on this condition.
Thank you for your constructive suggestion regarding the structure of the paper. We have revised the manuscript accordingly, expanding the algorithm section to explain OPUR’s workflow and implementation details more clearly, including surrogate target construction, probabilistic position selection, probe-loss screening and suffix optimization. We have also condensed the theoretical exposition while preserving the core results, allocating more space to the algorithmic mechanisms. We hope these revisions address your concern and make the method easier to follow. Please refer to the revised PDF for the updated structure and presentation.
Thank you for your review and the helpful comments on the theory–algorithm connection, variability across random seeds, computational cost, and position-selection mechanism. We address each point below.
Connection between π and OPUR
Thank you for pointing out that this connection needed clarification. Theorem 2 connects the gradient of log expected harmfulness to likelihood gradients under π. OPUR provides a practical surrogate for this target-selection role: bootstrap-style rollouts supply contexts grounded in current model behavior, target segments encode the attack objective, and probabilistic position selection and probe screening prioritize locally compatible targets. The retained contexts guide likelihood-based suffix optimization, while the added component ablations provide empirical support for this construction.
Evaluation across multiple random seeds
Thank you for highlighting the need to account for randomness. We have repeated the evaluation of all five methods using three random seeds on both models and all three benchmarks. We report average ASR (%) as mean ± standard deviation. The complete results are summarized below.
Results on Llama-3.1-8B-Instruct:
Results on Ministral-8B-Instruct-2410:
OPUR achieves the highest mean average ASR in all six model–benchmark combinations. These repeated-run results provide further evidence for its mean-performance advantage across the evaluated settings.
Runtime Computation
Thank you for requesting clearer computational-cost accounting. Each OPUR iteration generates Kopt rollouts, scores candidate positions, and evaluates candidate contexts using forward-only probe computations. Only retained contexts contribute to the target-span gradients used for suffix-candidate generation; candidate evaluation is also forward-only. Under the four-to-two configuration, up to 4Kopt contexts are probed and 2Kopt contribute to gradient computation. Compared to GCG, OPUR adds rollout context construction. Compared to UDora, it adds sampled-context exploration and screening. We have also added total-runtime comparisons and rollout-budget runtime ablations in the Runtime Analysis in Appendix D , documenting the time cost associated with the ASR improvements.
Relationship between Softmax, greedy, and random selection
Thank you for asking us to clarify the selection mechanism. Greedy and Softmax selection use the same insertion-position scores: greedy selection chooses the highest-scoring feasible positions, whereas Softmax converts these scores into sampling probabilities proportional to exp(rj/T). Uniform random selection ignores the scores. Lower temperatures concentrate probability on higher-scoring positions, while higher temperatures approach uniform selection over eligible positions. These probabilities guide surrogate-context construction; suffix gradients are subsequently computed from the retained contexts. We have added comparisons of all three strategies and temperature-sensitivity curves in Appendix C.
Clarifying the relationship in the manuscript
Thank you for emphasizing the need to explain this relationship explicitly in the paper. We have added a discussion following Eq. (8) and clarified the motivation and algorithm description in Section 4. The revised text explains the target-selection role of π, how OPUR’s components implement the corresponding design considerations, and how the component experiments empirically support the surrogate construction.