- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes VETA, a resource exhaustion attack on vision language models based on semantic image editing, aiming to improve cross model transferability of the attack. Using only black box feedback from a surrogate model, VETA learns semantic editing policies via reinforcement learning that induce target models to generate abnormally long responses.
Critical strengths
-
Practical attack formulation. VETA learns transferable image-editing policies through reinforcement learning, using only black-box response feedback without access to target model gradients.
-
Fairly broad evaluation. The attack is tested across diverse VLM architectures, with ablations on training stages and reward components, and measurements of real inference costs.
Critical weaknesses
-
The attack mechanism lacks sufficient validation. The paper fails to effectively distinguish between anomalies induced by OCR and the effects of other semantic edits. Consequently, it is difficult to determine whether the attack relies primarily on OCR-related recognition errors.
-
The contribution of reinforcement learning remains unclear. Since standard image editing alone can already significantly amplify the attack’s output, the existing baselines do not adequately control for the content and magnitude of the edits.
Questions for authors
- Could the authors provide an ablation that excludes text-based edits and report the attack efficacy of each of the four edit types under the final policy?
- Could the authors include a simple semantic editing baseline under the same edit constraints to verify the actual contribution of reinforcement learning?
- Minor: Figures 1 and 2 are somewhat stylized. Could the authors consider a simpler, more conventional style for Figures 1 and 2 to make the method easier to follow?