Wei Wang

This paper demonstrates that the Euston secure inference framework, which uses SVD-based matrix transmission to save bandwidth, leaks private input data by exploiting subspace leakage of random masks.

The paper proposes GREW, a novel Green-REd Watermarking framework that embeds ownership signals into recommender systems' intrinsic ranking process without requiring synthetic data, achieving robust protection against model extraction attacks.

TwinGate introduces a stateful dual-encoder defense framework using Asymmetric Contrastive Learning to detect malicious intent from fragmented, untraceable LLM queries with high recall and low false positives.

The paper systematizes the interaction between autonomous AI agents and blockchain platforms using a bidirectional trust framework, identifying significant gaps in current standards and proposing a taxonomy for future research.

The paper proposes SATA, a semantics-aware traffic augmentation framework, to significantly improve the generalization of website fingerprinting models by addressing variability in resource composition and cross-layer feature instability.

The paper proposes PCDM, a diffusion-based framework that enables highly stealthy and effective data poisoning attacks against Federated Learning systems, significantly degrading global performance while evading detection.

The paper introduces Babel, an efficient black-box attack framework that systematically exploits intrinsic safety gaps in LLMs by optimizing text obfuscation sampling, achieving state-of-the-art jailbreak success rates on commercial models.

This paper empirically evaluates the performance of the Polars DataFrame engine running within Intel SGX2 enclaves, finding that while the overall security overhead is manageable, the performance is significantly impacted by data loading and API choice.

The paper introduces SpikeWFM, a novel hybrid architecture combining spiking neural networks (SNNs) and transformers, which significantly improves the robustness and accuracy of wireless foundation models for channel prediction against noise and interference.

The paper proposes MemoAttack, a memory-driven black-box jailbreak framework that systematically models, evolves, and selects attack experiences to significantly enhance LLM jailbreaking success rates.