3 citations · 13 across the 22 of their papers we have counts for
25 papers
LEAF: LUT-aware Efficient Attention on FPGAs
Arianna Cox, Chang Sun, Lauri Laatu +7
We introduce Lookup-table (LUT)-aware Efficient Attention on FPGAs (LEAF). LEAF is the first nanosecond-scale LUT-aware transformer for FPGAs. Deploying transformers that are large…
Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models
Yupeng Qiu, Han Fang, Dhananjai Sharma +1
Low-Rank Adaptation (LoRA) has made diffusion model personalization affordable and widely shareable, but it also creates moderation risks when harmful or problematic content is not…
CASIAL: Geometric Distortion Robust Image Watermarking
Yupeng Qiu, Han Fang, Ee-Chien Chang
Deep learning-based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations remains limited. Such transforma…
Enhancing Stateful Detection of Adversarial Attacks with Soft-labels' Temporality and Robust Similarity Approximations
De Zhang Lee, Han Fang, Ee-Chien Chang
Stateful Detection (SD) mitigates adversarial attacks by determining whether a sequence of queries contains queries from a black-box adversary. Recent works, such as Blacklight and…
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
Mengyao Du, Han Fang, Haokai Ma +4
Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious i…
ResetEdit: Precise Text-guided Editing of Generated Image via Resettable Starting Latent
Hanyi Wang, Han Fang, Zheng Wang +2
Recent advances in diffusion models have enabled high-quality image generation, leading to increasing demand for post-generation editing that modifies local regions while preservin…
ResGuard: Enhancing Robustness Against Known Original Attacks in Deep Watermarking
Hanyi Wang, Han Fang, Yupeng Qiu +2
Deep learning-based image watermarking commonly adopts an "Encoder-Noise Layer-Decoder" (END) architecture to improve robustness against random channel distortions, yet it often ov…
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
Siyuan Liang, Yongcheng Jing, Yingjie Wang +3
Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence. Existing methods often fail under strong detecti…
TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
Mengyao Du, Han Fang, Haokai Ma +4
Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit…
Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier
Mengyao Du, Gang Yang, Han Fang +2
The widespread adoption of natural language processing techniques has led to an unprecedented growth of text classifiers across the modern web. Yet many of these models circulate w…
Removal Attack and Defense on AI-generated Content Latent-based Watermarking
De Zhang Lee, Han Fang, Hanyi Wang +1
Digital watermarks can be embedded into AI-generated content (AIGC) by initializing the generation process with starting points sampled from a secret distribution. When combined wi…
SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents
Siyuan Liang, Tianmeng Fang, Zhe Liu +5
With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal t…
Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents
Xuan Wang, Siyuan Liang, Zhe Liu +5
Mobile agents powered by vision-language models (VLMs) are increasingly adopted for tasks such as UI automation and camera-based assistance. These agents are typically fine-tuned u…
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
Xuan Wang, Siyuan Liang, Dongping Liao +6
Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training p…
WFCAT: Augmenting Website Fingerprinting with Channel-wise Attention on Timing Features
Jiajun Gong, Wei Cai, Siyuan Liang +3
Website Fingerprinting (WF) aims to deanonymize users on the Tor network by analyzing encrypted network traffic. Recent deep-learning-based attacks show high accuracy on undefended…
TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning
Siyuan Liang, Jiajun Gong, Tianmeng Fang +5
Website fingerprinting (WF) attacks, which covertly monitor user communications to identify the web pages they visit, pose a serious threat to user privacy. Existing WF defenses at…
Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
Siyuan Liang, Jiawei Liang, Tianyu Pang +5
Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static sett…
Object Detectors in the Open Environment: Challenges, Solutions, and Outlook
Siyuan Liang, Wei Wang, Ruoyu Chen +5
With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detector…
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
Siyuan Liang, Kuanrong Liu, Jiajun Gong +4
Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the ope…
Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs
Xiaoxia Li, Siyuan Liang, Jiyi Zhang +3
Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where craf…
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
Jiawei Liang, Siyuan Liang, Man Luo +4
Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed t…
Domain Bridge: Generative model-based domain forensic for black-box models
Jiyi Zhang, Han Fang, Ee-Chien Chang
In forensic investigations of machine learning models, techniques that determine a model's data domain play an essential role, with prior work relying on large-scale corpora like I…
Improving Adversarial Transferability by Stable Diffusion
Jiayang Liu, Siyu Zhu, Siyuan Liang +4
Deep neural networks (DNNs) are susceptible to adversarial examples, which introduce imperceptible perturbations to benign samples, deceiving DNN predictions. While some attack met…
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
Siyuan Liang, Mingli Zhu, Aishan Liu +3
Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learn…