19 citations · 50 across the 26 of their papers we have counts for
26 papers
Robustness-Aware Evaluation and Enhancement of Mutation-Based Fuzzing for Bug Discovery
Zirui Liu, Mengfan Xu, Juan Zhai +2
Mutation-based fuzzing is widely used to discover software vulnerabilities, but its randomness complicates rigorous evaluation and reliable bug detection. Prior work measures this…
CAROL: Context-Aware Online Learning for Fuzzer Scheduling
Zirui Liu, Mengfan Xu, Juan Zhai +2
Ensemble fuzzing runs multiple fuzzers on a target while a scheduler allocates CPU time among them. Existing schedulers base these decisions on compact summaries of past performanc…
False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models
Weipeng Jiang, Xiaoyu Zhang, Juan Zhai +3
Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs) remain largely unexplored. In this pap…
PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and Fuzz Optimization
Mingzhe Li, Renhao Zhang, Zhiyang Wen +4
Text-to-image (T2I) generative models such as Stable Diffusion and FLUX can synthesize realistic, high-quality images directly from textual prompts. The resulting image quality dep…
Rethinking Technology Stack Selection with AI Coding Proficiency
Xiaoyu Zhang, Weipeng Jiang, Shiqing Ma +5
Large language models (LLMs) are now an integral part of software development workflows and are reshaping the whole process. However, existing technology selection methods mainly f…
Mitigating Stylistic Biases of Machine Translation Systems via Monolingual Corpora Only
Xuanqi Gao, Weipeng Jiang, Juan Zhai +4
The advent of neural machine translation (NMT) has revolutionized cross-lingual communication, yet preserving stylistic nuances remains a significant challenge. While existing appr…
ASSURE: Metamorphic Testing for AI-powered Browser Extensions
Xuanqi Gao, Juan Zhai, Shiqing Ma +2
The integration of Large Language Models (LLMs) into browser extensions has revolutionized web browsing, enabling sophisticated functionalities like content summarization, intellig…
Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice
Gehao Zhang, Mingzhe Li, Eugene Bagdasarian +2
Large language models (LLMs) are increasingly used for code generation, making reliable identification of machine-generated code important for attribution, tracking, and misuse det…
EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models
Mingzhe Li, Kejing Xia, Gehao Zhang +5
Text-to-image generation models~(e.g., Stable Diffusion) have achieved significant advancements, enabling the creation of high-quality and realistic images based on textual descrip…
MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models
Xuanqi Gao, Siyi Xie, Juan Zhai +2
As Large Language Models (LLMs) evolve from passive text generators to active reasoning agents capable of interacting with external tools, the Model Context Protocol (MCP) has emer…
Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal
Weipeng Jiang, Juan Zhai, Shiqing Ma +4
In recent years, Large Language Models (LLMs) have faced increasing demands to selectively remove sensitive information, protect privacy, and comply with copyright regulations thro…
The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
Xiaoyu Zhang, Juan Zhai, Shiqing Ma +5
Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation. In this p…
Speculative Coreset Selection for Task-Specific Fine-tuning
Xiaoyu Zhang, Juan Zhai, Shiqing Ma +4
Task-specific fine-tuning is essential for the deployment of large language models (LLMs), but it requires significant computational resources and time. Existing solutions have pro…
Data-centric NLP Backdoor Defense from the Lens of Memorization
Zhenting Wang, Zhizhi Wang, Mingyu Jin +3
Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample…
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
Weipeng Jiang, Zhenting Wang, Juan Zhai +3
Despite prior safety alignment efforts, mainstream LLMs can still generate harmful and unethical content when subjected to jailbreaking attacks. Existing jailbreaking methods fall…
Efficient DNN-Powered Software with Fair Sparse Models
Xuanqi Gao, Weipeng Jiang, Juan Zhai +3
With the emergence of the Software 3.0 era, there is a growing trend of compressing and integrating large models into software systems, with significant societal implications. Regr…
Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
Yuan Xiao, Shiqing Ma, Juan Zhai +3
The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, withi…
CITADEL: Context Similarity Based Deep Learning Framework Bug Finding
Xiaoyu Zhang, Juan Zhai, Shiqing Ma +2
With the application of deep learning technology, tools of DL framework testing are in high demand. Existing DL framework testing tools have limited coverage of bug types. For exam…
From Effectiveness to Efficiency: Uncovering Linguistic Bias in Large Language Model-based Code Generation
Weipeng Jiang, Xuanqi Gao, Juan Zhai +4
Large Language Models (LLMs) have demonstrated promising capabilities for code generation. While existing benchmarks evaluate the correctness and efficiency of LLM-generated code,…
DREAM: Debugging and Repairing AutoML Pipelines
Xiaoyu Zhang, Juan Zhai, Shiqing Ma +1
Deep Learning models have become an integrated component of modern software systems. In response to the challenge of model design, researchers proposed Automated Machine Learning (…
CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement
Xuanqi Gao, Juan Zhai, Shiqing Ma +3
Due to the model aging problem, Deep Neural Networks (DNNs) need updates to adjust them to new data distributions. The common practice leverages incremental learning (IL), e.g., Cl…
UNICORN: A Unified Backdoor Trigger Inversion Framework
Zhenting Wang, Kai Mei, Juan Zhai +1
The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (D…
Rethinking the Reverse-engineering of Trojan Triggers
Zhenting Wang, Kai Mei, Hailun Ding +2
Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-eng…
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning
Zhenting Wang, Juan Zhai, Shiqing Ma
Deep neural networks are vulnerable to Trojan attacks. Existing attacks use visible patterns (e.g., a patch or image transformations) as triggers, which are vulnerable to human ins…