Xiangyu Zhang
~Xiangyu_Zhang3
18
论文总数
9.0
年均投稿
平均评分
接收情况12/18
会议分布
ICLR
8
NeurIPS
7
ICML
2
COLM
1
发表论文 (18 篇)
202512 篇
4
VERA: Variational Inference Framework for Jailbreaking Large Language Models
NeurIPS 2025Poster
4
$\mu$KE: Matryoshka Unstructured Knowledge Editing of Large Language Models
COLM 2025Poster
4
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
ICML 2025Poster
5
Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning
ICLR 2025Poster
4
ProSec: Fortifying Code LLMs with Proactive Security Alignment
ICML 2025Poster
4
Poisoning with A Pill: Circumventing Detection in Federated Learning
ICLR 2025Rejected
4
ASPIRER: Bypassing System Prompts with Permutation-based Backdoors in LLMs
ICLR 2025Rejected
4
TAI3: Testing Agent Integrity in Interpreting User Intent
NeurIPS 2025Poster
4
Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
ICLR 2025withdrawn
4
Combating Hidden Vulnerabilities in Computer Vision Tasks
ICLR 2025withdrawn
4
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis
ICLR 2025Rejected
3
Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
NeurIPS 2025Poster
20246 篇
4
When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
NeurIPS 2024Poster
4
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
NeurIPS 2024Poster
4
LLMDFA: Analyzing Dataflow in Code with Large Language Models
NeurIPS 2024Poster
4
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
NeurIPS 2024Poster
4
Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
ICLR 2024Poster
3
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
ICLR 2024withdrawn