activity
20202026
most citedDPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training

3 citations · 8 across the 6 of their papers we have counts for

collaborators
Showing cs.CRShow all

6 papers · 1 filter

cs.CR2026

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…

cs.CR2024

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…

cs.CR2023

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…

cs.CR2023

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…

cs.CR20222 cited

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…

cs.CR20202 cited

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…