VENOM first learns a contrastive space over server-observed embeddings, then builds a neighborhood graph and trains a surrogate bottom model to match targets and respect local geometry via a neighbor-matching loss alongside pointwise and feature-shape alignment to preserve the relational structure that defenses fail to erase.
This work presents DeepInvert, a semi-supervised embedding inversion attack that recovers original tokens from obfuscated representations with higher accuracy than prior methods, and reveals a task-dependent tension: obfuscation schemes preserving enough signal for utility also retain sufficient structure for inversion...
FISGuard reduces the ProjRes attack AUC to near the random-guessing level of 0.5 in most settings, while maintaining downstream task performance close to that of the undefended model and introducing only limited computational overhead, thereby achieving a favorable privacy--utility trade-off.
It is proved that, under an honest-majority assumption and a representation-level separation condition, RAGSentinel exactly recovers a poison-free majority-sized context.
Yueyang Quan, Anjun Gao, Yu Xia et al.· 0 citations
A novel black-box image embedding inversion attack that reconstructs high-fidelity images using only query access to the embedding model or API, and introduces an embedding-guided cross-attention mechanism, where image embeddings serve as conditional signals to steer the generation process.
Lichao Sun, Yun-Cheng Wu, Hai-Chao Sha et al.· Proceedings of the 32nd ACM...· 0 citations
The key idea is to induce the adversary to solve a misspecified inverse problem, in which no plausible label sequence in the sequence space can explain the observed gradients, by inducing inconsistency across three dimensions: objective, direction, and scale.
Shiyu Miao, Yunlong Mao, Zirui Huang et al.· 0 citations
This work reveals that backdoor behaviors tend to be absorbed by a simpler parallel branch when jointly trained with the main network, and proposes Trapping and Removing (TR), a simple yet effective training-time defense that introduces a lightweight shortcut branch as a "honeypot" to trap backdoor knowledge.
Zixuan Zhu, Rui Wang, Lihua Jing et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
