13 citations · 17 across the 11 of their papers we have counts for
12 papers
Speculating LLMs' Chinese Training Data Pollution from Their Tokens
Qingjie Zhang, Di Wang, Haoting Qian +7
Tokens are basic elements in the datasets for LLM training. It is well-known that many tokens representing Chinese phrases in the vocabulary of GPT (4o/4o-mini/o1/o3/4.5/4.1/o4-min…
When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
Cheng Wang, Gelei Deng, Xianglin Yang +2
Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and te…
ObfusBFA: A Holistic Approach to Safeguarding DNNs from Different Types of Bit-Flip Attacks
Xiaobei Yan, Han Qiu, Tianwei Zhang
Bit-flip attacks (BFAs) represent a serious threat to Deep Neural Networks (DNNs), where flipping a small number of bits in the model parameters or binary code can significantly de…
Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
Shujian Yang, Shiyao Cui, Chuanrui Hu +5
Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent…
FaceID-6M: A Large-Scale, Open-Source FaceID Customization Dataset
Shuhe Wang, Xiaoya Li, Jiwei Li +8
Due to the data-driven nature of current face identity (FaceID) customization methods, all state-of-the-art models rely on large-scale datasets containing millions of high-quality…
An Engorgio Prompt Makes Large Language Model Babble on
Jianshuo Dong, Ziyuan Zhang, Qingjie Zhang +7
Auto-regressive large language models (LLMs) have yielded impressive performance in many real-world tasks. However, the new paradigm of these LLMs also exposes novel threats. In th…
Understanding the Dark Side of LLMs' Intrinsic Self-Correction
Qingjie Zhang, Di Wang, Haoting Qian +7
Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic se…
COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation
Ziyuan Zhang, Han Qiu, Maosen Zhang +4
With the rapidly increasing number of satellites in space and their enhanced capabilities, the amount of earth observation images collected by satellites is exceeding the transmiss…
Defense against ML-based Power Side-channel Attacks on DNN Accelerators with Adversarial Attacks
Xiaobei Yan, Chip Hong Chang, Tianwei Zhang
Artificial Intelligence (AI) hardware accelerators have been widely adopted to enhance the efficiency of deep learning applications. However, they also raise security concerns rega…
A Unified Hardware-based Threat Detector for AI Accelerators
Xiaobei Yan, Han Qiu, Tianwei Zhang
The proliferation of AI technology gives rise to a variety of security threats, which significantly compromise the confidentiality and integrity of AI models and applications. Exis…
TPU as Cryptographic Accelerator
Rabimba Karanjai, Sangwon Shin, and Wujie Xiong +8
Cryptographic schemes like Fully Homomorphic Encryption (FHE) and Zero-Knowledge Proofs (ZKPs), while offering powerful privacy-preserving capabilities, are often hindered by their…
Memory DoS Attacks in Multi-tenant Clouds: Severity and Mitigation
Tianwei Zhang, Yinqian Zhang, Ruby B. Lee
In cloud computing, network Denial of Service (DoS) attacks are well studied and defenses have been implemented, but severe DoS attacks on a victim's working memory by a single hos…