- Rating
- 4
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper introduces hardware-triggered backdoors where a model is modified so that a pre-chosen input is classified correctly on one GPU but misclassified on another, with no input trigger, instead using the hardware's floating-point deviations. The attack shapes the decision boundary so the target sits at a near-tie, then searches over weight permutations and bit-flips for a candidate whose predictions disagree across devices. It is evaluated on four ImageNet models, five Nvidia GPUs and three data types, extended to multiple targets, one-vs-rest selectivity and CPU–GPU pairs, and tested against four defenses.
Critical strengths
- Success exceeds 94% on nearly all GPU pairs, models and data types including float32, one-vs-rest selectivity is above 90% for most configurations, and the ablation shows the hardware-specific step does real work. This is the central claim and it is convincingly established.
- The paper reports causal localisation, and honestly reports its success decaying at five targets, and defenses that work against it. In particular, fine-tuning removes nearly all backdoors.
Critical weaknesses
- Under AMP, success drops significantly. AMP is a common deployment default, so the attack is unreliable in many realistic settings. Since step 2 already scores candidates across multiple environments (as in one-vs-rest), AMP execution could have been added as another environment. Without this experiment, it is unclear whether the limitation is fundamental. Addressing this would make the attack considerably more practical.
Questions for authors
- Section 6 duplicates the target across the batch. What is success when it is co-batched with random inputs?
- The introduction says the backdoors "can withstand" input perturbations, batching and mixed precision. Section 6 shows that performance can be significantly weakened in these settings, so I would suggest refining the wording here to reflect this.
- If ULPs are measured on the normalised float32 tensor, well below a single 8-bit pixel step, does that imply the victim must reproduce preprocessing bit-for-bit?
2 comments
I appreciate the authors’ response. The clarifications to Q1 and Q3 make sense. For Q3, some text in the paper stating this assumption would be nice. For Q2, tightening the wording around robustness is an important change as well. Finally, regarding AMP, whatever the outcome at ICLR, I think an AMP evaluation would be a good experiment to run for a future version.
Dear reviewer,
Thank you for the positive feedback. We would like to address your questions:
Random inputs in different rows do not affect the calculation. The output for a specific sample only depends on the sample's values and its position inside the batch (and the batch size).
We will refine the wording here. We wanted to express that, given the fragility of floating-point noise, we were actually surprised to measure some "robustness" at all.
In a sense, yes. We assume that the adversary can either fully remodel the victim's preprocessing, or defines it themselves (e.g., as part of a larger software solution).
We agree that AMP is a common deployment setting and that the results in Section 6 should be framed more clearly. AMP deterministically executes selected operations in reduced precision, so from the attacker’s perspective it behaves like a distinct execution platform. In our defense section, we measured the transfer from a backdoor optimized for non-AMP execution to AMP-based inference, i.e., a setting where the attacker did not account for AMP. This drop therefore does not indicate a fundamental limitation. An attacker aware of AMP can include it as an additional environment. Tables 7 and 8 already show that the attack succeeds when targeting float16/bfloat16 execution directly. We will clarify this distinction in the revised version.