- Rating
- 4(+1)
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper proposes a novel gradient inversion attack in an honest-but-curious setting, that leverages low-rank structure of attention layer gradients, to recover input data. The attack optimizes against gradient-induced subspaces rather than matching full gradients. The proposed attack can be applied to both image and text modalities, in contrast to state-of-the-art work, DAGER, while showing robustness against existing defense mechanisms. The paper extends the attack to both causal and bidirectional attention mechanisms, while handing different challenges such as preventing recovery of duplicate tokens and sequences. The effectiveness of the proposed attack has been demonstrated through extensive experiments.
Critical strengths
-
The paper is well-motivated and clearly written. The related works discussed are sufficient.
-
The paper addresses a critical limitation of state-of-the-art work, DAGER (Petrov et al., 2024). DAGER is an exact gradient inversion attack, that can only be applied to text recovery, since it relies on a predefined vocabulary. The proposed attack, TIGER can be applied to multiple modalities.
-
TIGER is more robust than DAGER against the existing defense mechanisms like differential privacy and quantization as demonstrated in the experiments.
-
It considers an honest-but-curious adversary model, hence does not maliciously modify the protocol like Fowl et al., 2022, Fowl et al., 2023, Sami et al., 2026. Hence, the proposed attack can be successfully executed without raising any suspicion across the users.
Critical weaknesses
- In Corollary 4.1, the condition for a global minima is restricted in the sense that the total number of tokens must be less than or equal to . This restricts recovery in practical settings, where the number of training tokens can be in the order of thousands.
Questions for authors
-
In parameter-efficient fine-tuning settings like LoRA, adapter, the adversarial server has access to fine-tuning gradients only. For example, in LoRA, the server has access to gradients of low-rank matrices A, B only (MineGrad, Sami et al., 2026). How does corollary 4.1 change under such settings? How is the attack effectiveness being impacted?
-
When we have same first token in multiple sequences, does n’t the deduplication loss negatively impact the recovery of the same first token in the later sequences? Can you explain this further?
-
TIGER is an optimization-based attack whereas DAGER is an exact gradient inversion attack. In decoder architectures, how does total runtime for inversion compare against that of DAGER? This is particularly important for a resource-limited adversary.
I would consider raising the score if the above questions are clarified further.
5 comments
R3.4. (Q3) How does TIGER’s total runtime compare to DAGER’s?
We provide a detailed comparison in R4 of our Common Response. While DAGER is substantially faster on smaller batches, its runtime becomes highly unpredictable at B=8, with 2/10 batches exceeding our 8-hour timeout due to the combinatorial explosion of its discrete search space. In contrast, TIGER completes all batches, with runtime scaling approximately linearly with batch size (14.5 minutes at B=1 to 2.11 hours at B=8) and little variation across runs. Thus, TIGER trades off a higher typical runtime for substantially more predictable scaling, while maintaining comparable GPU memory usage. We also compare our runtime against optimization-based attacks such as LAMP, where TIGER achieves from 27 to 230x lower per-initialization iteration time across encoder and decoder models, while supporting substantially more parallel initializations by avoiding expensive second-order differentiation.
I thank the authors for providing detailed responses to my questions. Specially, I liked the solution to the deduplication loss concern - "allowing multiple sequences sharing the same first token to be recovered through their different second tokens." The improvements in the results are also impressive. Regarding LoRA fine-tuning as well, the detailed experimental results are promising. However, the authors show results for ranks 64 to 256. The LoRA paper (Hu et al., 2022) also reports results with smaller ranks as well (r=1,2,4,8). Even Sami et al., 2026 reports attack performance on smaller rank values. It would be nice to see how those small rank values impact the performance. I would appreciate if the authors could comment further on this/show some results. All the remaining concerns have been addressed.
We thank the reviewer for their constructive feedback and inquiries. We appreciate their recognition of TIGER's clarity, multimodal generality beyond text-only attacks like DAGER, and robustness against defenses under an honest-but-curious threat model. We address each concern in detail below.
R3.1. (Q1) How does LoRA training impact the theoretical considerations of Corollary 4.1 and TIGER’s practical performance?
We thank the reviewer for this question. As detailed in R3 of our Common Response, it is possible to extend TIGER to LoRA fine-tuning both theoretically and experimentally. We show that LoRA gradients retain information about the hidden-state subspaces, although their rank is limited by the LoRA rank r. Under the same rank assumptions as our original analysis, this yields a conservative recovery condition of T≤r(L−1)/L, analogous to the original condition involving the transformer dimension d. We further show that combining query, key, and value LoRA gradients can increase the available rank to 3r, extending this condition to T≤3r(L−1)/L. Experimentally, we evaluate TIGER on multimodal inputs using LoRA ranks 64, 128, and 256. At rank 128, TIGER achieves 97.7% image-token recovery, compared to 98.2% with full gradients. Remarkably, even at rank 64, where the number of tokens exceeds the LoRA rank, TIGER still recovers 89.3% of image tokens, although text reconstruction degrades substantially. As explained in R3, this is possible because the observed low-rank gradient subspaces preserve disproportionately more information about image tokens than text tokens, allowing TIGER to recover images even when T>r. By combining Q/K/V gradients at rank 64, image-token recovery increases to 98.4%, with 100 ROUGE-1/ROUGE-2 for the question. These results demonstrate that TIGER remains effective under LoRA fine-tuning, even beyond the regime where exact hidden-state span recovery is guaranteed, and that combining gradients from multiple projections can substantially mitigate the information loss introduced by low-rank adaptation. We refer the reviewer to R3 for the full theoretical analysis, experiments, and explanation of recovery when T>r.
R3.2. (W1) Is the theoretical necessity requirement imposed by Corollary 4.1 realistic and can it be alleviated?
We thank the reviewer for raising this point. We first clarify that the condition in Corollary 4.1 guarantees that the ground-truth input is the unique global minimum, but it does not restrict TIGER from finding good reconstructions, even if partial. Empirically, TIGER can also remain effective beyond the regime covered by our theory: in our LoRA experiments (R3 of the Common Response), the analogous condition T≤r is violated at rank 64, yet TIGER still recovers 89.3% of image tokens, because the observed gradient subspaces continue to carry a strong signal about the true hidden states. Finally, when the number of observed directions is the limiting factor, this limitation can be alleviated by combining gradients from multiple projections that share the same inputs. As in R3, one can fuse the Q/K/V gradients to triple the available rank and transform the condition into T<3r(Lmax−1)/Lmax, reaching >12,000 tokens for 7B+ models.
R3.3. (Q2) How is TIGER affected by a batch with multiple samples sharing a first token, given the presence of the deduplication loss?
In the current version of the paper, the first-token deduplication loss discourages recovering the same first token more than once. When multiple ground-truth sequences share that token, TIGER can still recover them, but may instead recover the same sentence multiple times rather than identifying all distinct sequences. This limitation directly affects reconstruction, particularly at larger batch sizes.
We have addressed this issue, as detailed in R1.2 of our response to reviewer y5UA. Specifically, for each of the first two token positions, we now recover up to B candidate continuations for each prefix, rather than selecting only one. We extend the rotated-subspace deduplication loss to these positions to encourage distinct continuations and discard duplicate candidates. This allows multiple sequences sharing the same first token to be recovered through their different second tokens. On Rotten Tomatoes at B=8, this improvement alone raises R-1/R-2 from 83.2/81.1 to 90.5/89.1. We will update the paper accordingly.