- Rating
- 4
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes Training Witnesses, a framework for verifying neural network training without reproducing the entire process. It uses lightweight parameter fingerprints to record training states. The authors evaluate the system on models ranging from 100M to 2B parameters. The results show strong detection rates under the tested attacks, with relatively low training overhead.
Critical strengths
-
Clear motivation. Reproducing large-scale training is expensive. The paper addresses this problem with a useful approach that could make training claims easier to verify.
-
Promising experimental results. The proposed fingerprints and selective replay is interesting. The experiments demonstrate its feasibility at billion-parameter scale, with only about 1.19× runtime overhead in the 2B model setting.
Critical weaknesses
None
Questions for authors
How effective is the method against attacks involving only a few targeted training updates? Could the authors clarify how much protection parameter sketching provides beyond random replay in such cases?
2 comments
I appreciate the authors' revisions and efforts. I have no further concerns.
Targeted training updates
For the case of a few targeted updates, consider the following casework. One of three things could occur:
To operationalize that these cases are indeed exhaustive, we refer to [1] and [2]. In particular, [1] highlights that a small, yet constant number of tokens are required for poisoning, a regime we reliably detect. [2] highlights that LoRA fine-tunes of poisoning occupy many singular directions, meaning an orthogonal projection type method can be more effective in detecting it. Even most recent works on post-training edits [3] requires the spiking activation of a few neurons which we detect with near certainty in Figure 14.
If the reviewer believes there's a form of attack missed, we'd love to discuss it.
[1] Souly, et al., “Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples.” arXiv preprint, 2510.07192, (2025).
[2] Chillimuntha, et al., “Associative vs. Distributional: Two Regimes of Backdoor Learning in LoRA-Adapted Code-Generation Models.” J. Cybersecurity Priv, (2026).
[3] Papailiopoulos, "Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents" (2026).