4 papers
TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
Yu Cheng, Yongkang Hu, Jiuan Zhou +8
Test-time evolution of agent memory represents a pivotal paradigm for advancing AGI, as it strengthens complex reasoning through experience accumulation without requiring parameter…
SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems
Kaihong Li, Huichi Zhou, Bin Ma +1
Recommender systems (RS) are widely used in e-commerce for personalized suggestions, yet their openness makes them susceptible to shilling attacks, where adversaries inject fake be…
Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models
Xinran Zheng, Xingzhi Qian, Huichi Zhou +4
Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations. These issues, exacerbate…
Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge
Wenhan Mu, Ling Xu, Shuren Pei +2
The widespread adoption of code language models in software engineering tasks has exposed vulnerabilities to adversarial attacks, especially the identifier substitution attacks. Al…