This paper trains a perturbation model with the objective of maintaining the geometric distance between the original and adversarial document embeddings, while also maximizing the token-level dissimilarity be-tween the original and adversarial documents.
The results indicate that Micro-Collaborative Poisoning is not driven by a single dominant poisoned passage, but by the accumulation of weak adversarial signals across retrieved sources, which achieves downstream influence while leaving a weaker explicit poisoning signature than direct poisoning.
Pedro Pereira, Eva Maia, Isabel Praça· 0 citations
DSPrompt is proposed, a Dynamic Soft Prompt defense framework that directly reshapes the retriever's embedding semantics, without modifying the retrieval pipeline, and is consistently outperforming existing defense baselines at a fraction of their computational cost.
Chang Liu, Y. Lai, Ming-Yue Cui et al.· 0 citations
Deep Supervised Adversarial Robust Hashing (DSARH), an end-to-end framework that leverages similarity matrices and learnable hash codes to construct gradient-based worst-case perturbations, enabling efficient adversarial training and robust feature learning for retrieval, is proposed.
Xing-Wei Zhang, Gang Zhou, Xiaolong Zheng et al.· IEEE Transactions on Pattern...· 0 citations
A set of robust features that capture stable domain characteristics, including lexical word validity, homoglyph disguises, brand impersonation, subdomain depth, character entropy, and transport-related signals are proposed, which substantially improves robustness under adversarial conditions.
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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
