8 papers
DLR: Zero-Inference-Cost Latent Residuals for Low-Rank Pre-Training
Dong Wang, Wenwu Tang, Yun Cheng +1
Large language models have driven recent progress in language and multimodal AI, yet pre-training them at scale is prohibitively expensive. Low-rank pre-training, which factorizes…
Partitioning for Intrinsic Model Inversion Resistance in Collaborative Inference
Rongke Liu, Youwen Zhu, Lei Zhou +2
In collaborative inference (CI), transmitting intermediate representations from edge devices enables model inversion attacks (MIA) that reconstruct the original inputs , whi…
Cut Less, Fold More: Model Compression through the Lens of Projection Geometry
Olga Saukh, Dong Wang, Haris Å ikiÄ +2
Compressing neural networks without retraining is vital for deployment at scale. We study calibration-free compression through the lens of projection geometry: structured pruning i…
AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
Yanjie Li, Yiming Cao, Dong Wang +1
Multimodal agents built on large vision-language models (LVLMs) are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection, especially throug…
Gradient-Free Adversarial Purification with Diffusion Models
Xuelong Dai, Dong Wang, Xiuzhen Cheng +1
Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training r…
Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach
Yingze Li, Xianglong Liu, Dong Wang +4
Learned cardinality estimators show promise in query cardinality prediction, yet they universally exhibit fragility to training data drifts, posing risks for real-world deployment.…