48 citations · 144 across the 25 of their papers we have counts for
26 papers
Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution
Xiangzhe Xu, Hanxi Guo, Guangyu Shen +2
Natural-language workflows offer a software-like interface for agents: domain experts can write reusable procedures, and agents can execute them as instructions. This promise is no…
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…
From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
Guangyu Shen, Siyuan Cheng, Xiangzhe Xu +4
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Exi…
ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants
Xiangzhe Xu, Guangyu Shen, Zian Su +9
AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecuri…
MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation
Lu Yan, Zhuo Zhang, Xiangzhe Xu +5
Large language models (LLMs) have democratized software development, reducing the expertise barrier for programming complex applications. This accessibility extends to malicious so…
AuthGuard: Generalizable Deepfake Detection via Language Guidance
Guangyu Shen, Zhihua Li, Xiang Xu +6
Existing deepfake detection techniques struggle to keep-up with the ever-evolving novel, unseen forgeries methods. This limitation stems from their reliance on statistical artifact…
CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs
Hanxi Guo, Siyuan Cheng, Kaiyuan Zhang +2
Large language models (LLMs) have become integral to modern software development, producing vast amounts of AI-generated source code. While these models boost programming productiv…
CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling
Kaiyuan Zhang, Siyuan Cheng, Guangyu Shen +5
Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (g…
ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs
Lu Yan, Siyuan Cheng, Xuan Chen +4
Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In thi…
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
Siyuan Cheng, Guangyu Shen, Kaiyuan Zhang +5
Deep neural networks (DNNs) have demonstrated effectiveness in various fields. However, DNNs are vulnerable to backdoor attacks, which inject a unique pattern, called trigger, into…
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
Siyuan Cheng, Guanhong Tao, Yingqi Liu +7
Backdoor attack poses a significant security threat to Deep Learning applications. Existing attacks are often not evasive to established backdoor detection techniques. This suscept…
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Guangyu Shen, Siyuan Cheng, Kaiyuan Zhang +6
Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities. As they find incr…
Opening A Pandora's Box: Things You Should Know in the Era of Custom GPTs
Guanhong Tao, Siyuan Cheng, Zhuo Zhang +3
The emergence of large language models (LLMs) has significantly accelerated the development of a wide range of applications across various fields. There is a growing trend in the c…
Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs
Zhuo Zhang, Guangyu Shen, Guanhong Tao +2
Large Language Models (LLMs) are now widely used in various applications, making it crucial to align their ethical standards with human values. However, recent jail-breaking method…
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang +8
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training. However,…
ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP
Lu Yan, Zhuo Zhang, Guanhong Tao +4
Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to mi…
Detecting Backdoors in Pre-trained Encoders
Shiwei Feng, Guanhong Tao, Siyuan Cheng +6
Self-supervised learning in computer vision trains on unlabeled data, such as images or (image, text) pairs, to obtain an image encoder that learns high-quality embeddings for inpu…
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
Siyuan Cheng, Guanhong Tao, Yingqi Liu +8
Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of imp…
Backdoor Vulnerabilities in Normally Trained Deep Learning Models
Guanhong Tao, Zhenting Wang, Siyuan Cheng +7
We conduct a systematic study of backdoor vulnerabilities in normally trained Deep Learning models. They are as dangerous as backdoors injected by data poisoning because both can b…
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
Kaiyuan Zhang, Guanhong Tao, Qiuling Xu +8
Federated Learning (FL) is a distributed learning paradigm that enables different parties to train a model together for high quality and strong privacy protection. In this scenario…
DECK: Model Hardening for Defending Pervasive Backdoors
Guanhong Tao, Yingqi Liu, Siyuan Cheng +5
Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They…
Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense
Guangyu Shen, Yingqi Liu, Guanhong Tao +5
We develop a novel optimization method for NLPbackdoor inversion. We leverage a dynamically reducing temperature coefficient in the softmax function to provide changing loss landsc…
EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry
Yingqi Liu, Guangyu Shen, Guanhong Tao +3
Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features…
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
Guangyu Shen, Yingqi Liu, Guanhong Tao +5
Back-door attack poses a severe threat to deep learning systems. It injects hidden malicious behaviors to a model such that any input stamped with a special pattern can trigger suc…