16 papers
Cross-Session Decomposition Attacks: Scaling Risk and Intent-Aligned Retrieval Defense
Disen Liao, Yihan Wang, Freda Shi +1
Scaling laws are usually read as a capability story: lower language-modeling loss yields more useful models. We study a safety consequence of this mechanism in \emph{cross-session…
VeriPilot: An LLM-Powered Verilog Debugging Framework
Yihan Wang, Cheng Liu, Jiazheng Zhang +4
Verilog debugging remains one of the most time-consuming stages in digital circuit design. Recent advances in Large Language Models (LLMs) have enabled automated debugging; however…
Extracting Training Data from Diffusion Language Models via Infilling
Yihan Wang, N. Asokan
Memorization in large language models has been studied almost exclusively through prefix-conditioned extraction, a natural choice for autoregressive models. However, diffusion lang…
AnalogRetriever: Learning Cross-Modal Representations for Analog Circuit Retrieval
Yihan Wang, Lei Li, Yao Lai +2
Analog circuit design relies heavily on reusing existing intellectual property (IP), yet searching across heterogeneous representations such as SPICE netlists, schematics, and func…
Towards Robust Content Watermarking Against Removal and Forgery Attacks
Yifan Zhu, Yihan Wang, Xiao-Shan Gao
Generated contents have raised serious concerns about copyright protection, image provenance, and credit attribution. A potential solution for these problems is watermarking. Recen…
Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode
Zeyuan He, Yupeng Chen, Lang Lin +7
Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation efficiency. Beyond the utility benefit…
ResMAS: Resilience Optimization in LLM-based Multi-agent Systems
Zhilun Zhou, Zihan Liu, Jiahe Liu +5
Large Language Model-based Multi-Agent Systems (LLM-based MAS), where multiple LLM agents collaborate to solve complex tasks, have shown impressive performance in many areas. Howev…
QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
Hainan Fang, Yuanbo Wen, Jun Bi +8
Compilers, while essential, are notoriously complex systems that demand prohibitively expensive human expertise to develop and maintain. The recent advancements in Large Language M…
Are Targeted Data Poisoning Attacks as Effective as We Think?
William Xu, Chenyu Zhang, Yihan Wang +5
Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack succ…
Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
Shuang Liu, Yihan Wang, Yifan Zhu +2
Wasserstein distributionally robust optimization (WDRO) optimizes against worst-case distributional shifts within a specified uncertainty set, leading to enhanced generalization on…
BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
Yihan Wang, Yiwei Lu, Xiao-Shan Gao +2
Availability attacks, or unlearnable examples, are defensive techniques that allow data owners to modify their datasets in ways that prevent unauthorized machine learning models fr…
Evaluating Zero-Shot Long-Context LLM Compression
Chenyu Wang, Yihan Wang, Kai Li
This study evaluates the effectiveness of zero-shot compression techniques on large language models (LLMs) under long-context. We identify the tendency for computational errors to…
MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation
Yihan Wang, Yiwei Lu, Guojun Zhang +4
Machine unlearning offers effective solutions for revoking the influence of specific training data on pre-trained model parameters. While existing approaches address unlearning for…
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
Yihan Wang, Yifan Zhu, Xiao-Shan Gao
Availability attacks can prevent the unauthorized use of private data and commercial datasets by generating imperceptible noise and making unlearnable examples before release. Idea…
Game-Theoretic Unlearnable Example Generator
Shuang Liu, Yihan Wang, Xiao-Shan Gao
Unlearnable example attacks are data poisoning attacks aiming to degrade the clean test accuracy of deep learning by adding imperceptible perturbations to the training samples, whi…
Data-Dependent Stability Analysis of Adversarial Training
Yihan Wang, Shuang Liu, Xiao-Shan Gao
Stability analysis is an essential aspect of studying the generalization ability of deep learning, as it involves deriving generalization bounds for stochastic gradient descent-bas…