- Rating
- 2
- Confidence
- 4(+1)
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces SEMA-Auto, a multi-turn jailbreak model that reads the target model’s responses, generates follow-up prompts, and decides when to stop. Training consists of two stages. First, the model follows a self-generated static attack plan, while an external judge provides labels for its continue-or-stop decisions for supervised fine-tuning. Second, the method combines GRPO, guided by final-response rewards, with a supervised loss on decision tokens to improve both attack success and stopping accuracy.
Critical strengths
SEMA-Auto can detect attack success and stop without an external evaluator at inference time, substantially reducing evaluation costs. It also achieves successful attacks in very few rounds.
Critical weaknesses
-
The motivation needs clarification. The Abstract and Section 1 highlight the computational costs of in-loop evaluators and the risk of evaluator hacking. However, training still relies heavily on GPT-4.1 to compute response scores and generate decision labels. How does this reliance align with the stated motivation? Could bias or drift in the external judge be passed on to SEMA-Auto through the reward signal and decision supervision loss ?
-
The overall cost advantage is unclear. With samples per query, 416 queries, and three epochs, training involves tens of thousands of multi-turn trajectories and extensive evaluation by GPT-4.1. Please report the total token usage, number of API calls, and financial cost of training. How much inference is needed for the savings to offset these upfront costs, compared with using a lightweight in-loop evaluator?
-
The methodological novelty appears limited. SFT on synthetic data and RL with an auxiliary token-level cross-entropy loss are established techniques in reasoning, agent search, and tool use. SEMA-Auto applies this framework to binary continue-or-stop decisions in jailbreak attacks. What is the core algorithmic contribution beyond applying these techniques to this task?
-
The diversity and adaptability of the learned attacks remain unclear. SEMA-Auto appears to rely mainly on rephrasing the same request. How does its attack success rate change when the target model uses defenses such as semantic drift detection or intent restoration? Can SEMA-Auto move beyond fixed prompting patterns and adapt its strategy based on the target model’s feedback?
Questions for authors
please see the Weaknesses.
8 comments
W2 — Training cost vs. inference savings
We thank the reviewer for raising this. We count every call made in the two training stages. The training-time victim, Llama-3.1-8B-Instruct, is served locally, so the only API calls in training are those of the reward model that computes R_IDA. It scores every victim reply, so it is called once per adversarial turn. The table below compares the calls and tokens of SEMA-Auto with SEMA and TRACE. Attacker tokens are the tokens the attacker generates in reinforcement learning.
| Attacker | Stage | Trajectories | Victim calls | API calls for reward | API tokens for reward | Attacker tokens |
|---|---|---|---|---|---|---|
| SEMA | Reinforcement learning | 34,272 | 235,501 | 34,272 | 64.8M | 16.8M |
| TRACE | Reinforcement learning | 4,160 | 15,355 | - | - | 0.8M |
| SEMA-Auto | Synthetic bootstrap tuning | 6,656 | 29,827 | 29,827 | 71.4M | - |
| SEMA-Auto | Reinforcement learning | 34,272 | 110,267 | 110,267 | 268.7M | 4.5M |
| SEMA-Auto | Total | 40,928 | 140,094 | 140,094 | 340.1M | 4.5M |
Synthetic bootstrap tuning executes 6.7K plans of 4.5 turns on average, 16 for each of the 416 training queries. Reinforcement learning runs 51 steps of 24 queries with G = 28, which samples 34K trajectories of 3.2 turns on average. The two stages of SEMA-Auto call the API reward model 140K times, with 340M tokens in total.
We report the cost in API calls and tokens rather than in dollars. The price of the same tokens and GPU hours differs across providers and changes over time, so a dollar figure would hold for one provider at one date, while the counts above give the cost at any price. For compute, the reinforcement-learning stage of SEMA-Auto runs for 1.6 hours on 8 B200 GPUs, against 3.6 hours on 8 B200 GPUs for SEMA and 2.0 hours on 5 B200 GPUs for TRACE.
After training, SEMA-Auto makes no API call, whereas training-free interactive attacks, such as Crescendo, call an API model as their planner/attacker, their in-loop evaluator, or both, in every attack. The table below shows their calls per attack beyond the victim calls, averaged over the five victims and both datasets in the paper's Table 1. At these rates, Crescendo and GOAT make as many API calls as the whole training of SEMA-Auto within 13K and 14K attacks, FITD within at most 4.2K and X-Teaming within 34K. For reference, evaluating one attacker's ASR with 10 attempts on AdvBench against ten victims takes 52K attacks.
| Attacker | API models | Avg. turns | API calls per attack | Attacks to reach 140K API calls |
|---|---|---|---|---|
| Crescendo | GPT-4o (attacker, in-loop evaluator) | 5.3 | 10.5 | 13.3K |
| GOAT | GPT-4o-mini (attacker) | 10.0 | 10.0 | 14.0K |
| FITD | GPT-4o-mini (attacker) | 9.5 | ≥ 33 | ≤ 4.2K |
| X-Teaming | GPT-4.1 (planner), GPT-4o (in-loop evaluator) | 3.2 | 4.2 | 33.7K |
We note that during its attack, FITD also generates intermediate prompts and removes the turns the victim refuses, and the calls for these steps are not recorded, so its count in the table is a lower bound.
A lightweight in-loop evaluator that runs locally, such as the HarmBench Classifier used by TRACE and TROJail, makes no API call, so it leaves no API cost to offset. The API calls in our training come from the choice of reward model, GPT-4.1 computing R_IDA, which we take from SEMA, not from learning to stop. The decision target needs only a score of each reply and a threshold, which a local classifier can provide as well, and TRACE trains with a local classifier as its reward. Against such an evaluator, what SEMA-Auto saves is the evaluator's computation at every turn. In the cost analysis of the appendix, against GPT-oss-120B on HarmBench, TRACE runs its 13B in-loop evaluator after every turn and stops after 6.5 turns on average, taking 1.2 hours for the 159 requests. SEMA-Auto stops after 3.5 turns and takes 30.9 minutes.
We have added this analysis to the revision in Appendix D.3.
W3 — Limited methodological novelty
We thank the reviewer for relating our method to techniques used in reasoning, agent search, and tool use, which lets us state its algorithmic contribution more precisely. We acknowledge that both forms have been adopted by prior work: supervised fine-tuning on self-generated data, and a supervised term added to the RL loss. We do not claim either form as part of our novelty. The algorithmic contribution is to train the two outputs of one policy with separate signals: the attack by RL against the jailbreak reward, and the decision by supervision against an absolute per-turn label derived from the same reward.
This differs from how prior work combines the two. In tool use, for example, Hao et al. (2026) alternate RL with phases of supervised fine-tuning on whole ground-truth trajectories of the task, so that the policy imitates a reference solution. A jailbreak has no ground-truth trajectory to imitate. The cross-entropy of SEMA-Auto supervises one action of the policy itself, the decision, at every turn of the attacker's own rollouts, with a label read off the reward the run already computes, and the attack is left entirely to RL.
Our method is therefore not an existing technique borrowed from another field and applied to this task. In fact, it was motivated by our observations and analysis of decision collapse in Section 3.2. There, we find that reward and advantage shaping act only on the decisions a rollout samples, and that GRPO folds decision correctness into a group-relative signal, so once one action stops being sampled, no term placed on the decision can restore it. The decision therefore needs an absolute signal that does not pass through sampling, which supervision provides. We have also explored applying other techniques, including the loss masking of AdaCoT and the decoupled normalization of GDPO, but they do not address the decision collapse in our experiments.
Beyond the algorithm, the paper also contributes by proposing the autonomous attack paradigm, an interactive attacker that decides by itself when to stop and calls no evaluator in the loop, and by identifying and analyzing decision collapse in training such an attacker.
W1 — Reliance on GPT-4.1 in training
We thank the reviewer for raising this. We would like to kindly clarify the motivation stated in the paper, which concerns the in-loop evaluator at test time:
Either way, the reported result is sensitive to the in-loop evaluator. We note that we do not argue that such evaluators are unreliable and should be abandoned, which would indeed contradict training with one. Our point concerns their place in the test-time loop, where they make the reported result depend on the evaluator chosen rather than on the core attacker that generates the adversarial prompts. In trained SEMA-Auto, the attacker makes the stopping decision itself, independently of the final judge. Using response scores as the training reward therefore does not conflict with this motivation, which concerns test time alone.
If a training reward has bias or drift, it will be passed on to the attacker, as it is for any method trained with a reward, including the attack content of every learned attacker. Using such scores as the reward is common to learned attackers: SEMA, TRACE, TROJail, and Jailbreak-R1 are all trained with a judge reward. SEMA-Auto uses no additional evaluator, and it is trained to terminate when the reward RIDA≥τ and to continue otherwise. We argue that our learning to stop would not add a further source of bias, because the decision-supervised objective pulls in the same direction as the attack objective. Training on this reward already assumes that it moves the attack toward stronger jailbreaks, so a high reward is a reasonable signal to stop. The question therefore returns to the quality of the reward for jailbreak attacks, which is not the main focus of this work. In fact, nothing in our method is specific to RIDA, and our method needs only a score and a threshold, so a better reward can be used in its place without other changes. We have added a clarification in our revision (Appendix B.4).