45 citations · 95 across the 23 of their papers we have counts for
19 papers · 1 filter
Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
Kaikai Zhang, Zihan Zhang, Yuchong Xie +4
Autonomous LLM agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a subset under a finite budget. W…
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Zihan Zhang, Shuangjie Yao, Zesen Liu +8
Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similarity betwee…
Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
Zesen Liu, Zihan Zhang, Dongdong She
Summarization-based prompt compression is increasingly used by LLM agents to shorten long, distributed contexts, but it shifts the security boundary: filters inspect the pre-compre…
Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM Agents
Mingyu Luo, Zihan Zhang, Zesen Liu +7
LLM agents convert model outputs into consequential actions, including communications, code changes, and financial transactions. Developers often trust evidence such as test result…
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
Zhixiang Zhang, Zesen Liu, Yuchong Xie +2
Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft. By utilizing semantic embedding vec…
QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents
Yuchong Xie, Zesen Liu, Mingyu Luo +7
Modern coding agents integrated into IDEs orchestrate powerful tools and high-privilege system access, creating a high-stakes attack surface. Prior work on Indirect Prompt Injectio…
When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents
Zesen Liu, Zhixiang Zhang, Yuchong Xie +1
Prompt compression is increasingly deployed in LLM agents to reduce latency and cost, but it also determines what the backend LLM ultimately sees. We show that, when trusted and un…
Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
Yuchong Xie, Mingyu Luo, Zesen Liu +7
Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation o…
ZTaint-Havoc: From Havoc Mode to Zero-Execution Fuzzing-Driven Taint Inference
Yuchong Xie, Wenhui Zhang, Dongdong She
Fuzzing is a widely used technique for discovering software vulnerabilities, but identifying hot bytes that influence program behavior remains challenging. Traditional taint analys…
Empc: Effective Path Prioritization for Symbolic Execution with Path Cover
Shuangjie Yao, Dongdong She
Symbolic execution is a powerful program analysis technique that can formally reason the correctness of program behaviors and detect software bugs. It can systematically explore th…
Comment on Revisiting Neural Program Smoothing for Fuzzing
Dongdong She, Kexin Pei, Junfeng Yang +2
MLFuzz, a work accepted at ACM FSE 2023, revisits the performance of a machine learning-based fuzzer, NEUZZ. We demonstrate that its main conclusion is entirely wrong due to severa…
FOX: Coverage-guided Fuzzing as Online Stochastic Control
Dongdong She, Adam Storek, Yuchong Xie +3
Fuzzing is an effective technique for discovering software vulnerabilities by generating random test inputs and executing them against the target program. However, fuzzing large an…
NeuDep: Neural Binary Memory Dependence Analysis
Kexin Pei, Dongdong She, Michael Wang +6
Determining whether multiple instructions can access the same memory location is a critical task in binary analysis. It is challenging as statically computing precise alias informa…
: Rigorous and Efficient Directed Greybox Fuzzing
Abhishek Shah, Dongdong She, Samanway Sadhu +3
Directed greybox fuzzing is a popular technique for targeted software testing that seeks to find inputs that reach a set of target sites in a program. Most existing directed greybo…
Effective Seed Scheduling for Fuzzing with Graph Centrality Analysis
Dongdong She, Abhishek Shah, Suman Jana
Seed scheduling, the order in which seeds are selected, can greatly affect the performance of a fuzzer. Existing approaches schedule seeds based on their historical mutation data,…
Fine Grained Dataflow Tracking with Proximal Gradients
Gabriel Ryan, Abhishek Shah, Dongdong She +2
Dataflow tracking with Dynamic Taint Analysis (DTA) is an important method in systems security with many applications, including exploit analysis, guided fuzzing, and side-channel…
Neutaint: Efficient Dynamic Taint Analysis with Neural Networks
Dongdong She, Yizheng Chen, Abhishek Shah +2
Dynamic taint analysis (DTA) is widely used by various applications to track information flow during runtime execution. Existing DTA techniques use rule-based taint-propagation, wh…
On Training Robust PDF Malware Classifiers
Yizheng Chen, Shiqi Wang, Dongdong She +1
Although state-of-the-art PDF malware classifiers can be trained with almost perfect test accuracy (99%) and extremely low false positive rate (under 0.1%), it has been shown that…
NEUZZ: Efficient Fuzzing with Neural Program Smoothing
Dongdong She, Kexin Pei, Dave Epstein +3
Fuzzing has become the de facto standard technique for finding software vulnerabilities. However, even state-of-the-art fuzzers are not very efficient at finding hard-to-trigger so…