16 citations · 49 across the 12 of their papers we have counts for
13 papers
Training-Data Extraction from Genomic Language Models
Tianhao Mao, Zihao Wang, Dongfang Zhao +3
Genomic language models generate long nucleotide continuations from short prefixes, exposing a direct route for studying training-sequence extraction through the generation interfa…
When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning
Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2
Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior work often attributes this fai…
LLM-Enhanced Software Patch Localization
Jinhong Yu, Yi Chen, Di Tang +4
Open source software (OSS) is integral to modern product development, and any vulnerability within it potentially compromises numerous products. While developers strive to apply se…
DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
Zihao Wang, Rui Zhu, Dongruo Zhou +4
Recent developments have underscored the critical role of \textit{differential privacy} (DP) in safeguarding individual data for training machine learning models. However, integrat…
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
Xiaoyi Chen, Siyuan Tang, Rui Zhu +7
The rapid advancements of large language models (LLMs) have raised public concerns about the privacy leakage of personally identifiable information (PII) within their extensive tra…
Large Language Model Soft Ideologization via AI-Self-Consciousness
Xiaotian Zhou, Qian Wang, Xiaofeng Wang +2
Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, few studies have addressed the LLM threat and vulnerab…
MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion
Zilong Lin, Zhengyi Li, Xiaojing Liao +2
As a prominent instance of vandalism edits, Wiki search poisoning for illicit promotion is a cybercrime in which the adversary aims at editing Wiki articles to promote illicit busi…
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
Rui Zhu, Di Tang, Siyuan Tang +4
Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model di…
Stealthy Peers: Understanding Security Risks of WebRTC-Based Peer-Assisted Video Streaming
Siyuan Tang, Eihal Alowaisheq, Xianghang Mi +3
As an emerging service for in-browser content delivery, peer-assisted delivery network (PDN) is reported to offload up to 95\% of bandwidth consumption for video streaming, signifi…
Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
Rui Zhu, Di Tang, Siyuan Tang +2
In this paper, we present a simple yet surprisingly effective technique to induce "selective amnesia" on a backdoored model. Our approach, called SEAM, has been inspired by the pro…
Understanding Impacts of Task Similarity on Backdoor Attack and Detection
Di Tang, Rui Zhu, XiaoFeng Wang +2
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defend…
Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models
Jiawei Liu, Yangyang Kang, Di Tang +5
Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of g…
Confidential Attestation: Efficient in-Enclave Verification of Privacy Policy Compliance
Weijie Liu, Wenhao Wang, Xiaofeng Wang +9
A trusted execution environment (TEE) such as Intel Software Guard Extension (SGX) runs a remote attestation to prove to a data owner the integrity of the initial state of an encla…