- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents I2VShield, a protection method against I2V manipulation of images based on adversarial examples. The paper addresses why existing protection methods against T2I models are not directly applicable to I2V models. First, the paper shows that optimization that disrupts the internal latent of VAE encoders is not applicable to I2V models. Second, T2I protection methods that use random time steps are not applicable to I2V models. To this end, the paper proposes I2VShield, which focuses adversarial optimization budgets on a single time step. Across various benchmarks, the proposed method outperforms existing SoTA protection methods against both T2I and I2V models.
Critical strengths
- The paper presents a neat analysis on why existing protection methods on T2I models do not transfer directly to I2V models. Instead of a simply argument, this analysis adds value on how protection against I2V models should be designed.
- The proposed method is evaluated against a wide range of I2V models and is also compared with various methods against both T2I and I2V.
- The proposed method heavily outperforms existing SoTA methods, including protections against both T2I and I2V models.
Critical weaknesses
- Technical contributions. Technical contributions of the paper are limited. Instead of optimizing the adversarial examples over all time steps, the paper uses a single time step. This is an approach taken by DiffusionGuard [1], which is a method targeted for T2I model yet uses a single time step.
- Size of evaluation set. 80 image-prompt pairs for evaluation seems too small. I2VGuard and Anti-I2V use 300 and 5,000 data pairs, respectively, which are far larger than the dataset size used in this paper.
- Bypassing protection. Since the proposed method focuses adversarial optimization only on a single time step, it brings a new level of manipulation, where the adversary can intentionally bypass the target time step used during optimization. For example, the adversary may use SDEdit to start sampling from a partially noised latent of the protected image, so that is never evaluated during generation. The paper needs evaluation on the robustness of protection against such scenario.
[1] Choi et al., DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing, ICLR 2025
Questions for authors
- Please clarify the technical contributions of the work, especially compared to DiffusionGuard.
- Would it be possible for an adversary to break the protection by bypassing the time step used for optimization? If so, would the proposed method remain robust?