Search results
-
Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning
of data duplication on the unlearning process remains largely unexplored. This paper addresses this ...admin - October 14, 2025 - 4:14 pm
-
Digital Security Perceptions and Practices Around the World: A WEIRD versus Non-WEIRD Comparison
Franziska Herbert, Ruhr University Bochum; Collins W. Munyendo, The George Washington University and Max Planck Institute for Security and Privacy; Jonas Hielscher, Ruhr University Bochum; Steffen Becker, Ruhr University Bochum and Max Planck Institute fo ...admin - October 14, 2025 - 4:59 pm
-
Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
the model can do and what it is willing to do. In this paper, we introduce a novel jailbreak attack ...admin - October 14, 2025 - 4:31 pm
-
DeepFold: Efficient Multilinear Polynomial Commitment from Reed-Solomon Code and Its Application to Zero-knowledge Proofs
Yanpei Guo, Xuanming Liu, Kexi Huang, Wenjie Qu, Tianyang Tao, and Jiaheng Zhang, National University of Singapore This work presents Deepfold, a novel multilinear polynomial commitment scheme (PCS) based on Reed-Solomon code that offers optimal prover ti ...admin - October 14, 2025 - 4:16 pm
-
Cyber-Physical Deception Through Coordinated IoT Honeypots
Chongqi Guan and Guohong Cao, The Pennsylvania State University As Internet of Things (IoT) devices become widely deployed, they face numerous threats due to the inherent vulnerabilities and interconnected nature of these devices. One effective approach t ...admin - October 14, 2025 - 4:14 pm
-
Careless Retention and Management: Understanding and Detecting Data Retention Denial-of-Service Vulnerabilities in Java Web Containers
containers, which is defined as Data Retention DoS (DRDoS) in this paper. To the best of our knowledge, there ... paper, we design and implement a novel static analysis approach, called DR. D, to detect and assess DRDoS ...admin - October 14, 2025 - 3:49 pm
-
Efficient 2PC for Constant Round Secure Equality Testing and Comparison
Tianpei Lu, The State Key Laboratory of Blockchain and Data Security, Zhejiang University; Xin Kang, Xidian University; Bingsheng Zhang, The State Key Laboratory of Blockchain and Data Security, Zhejiang University; and Hangzhou High-Tech Zone (Binjiang) ...admin - October 14, 2025 - 4:19 pm
-
When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs
Hanna Kim, Minkyoo Song, Seung Ho Na, Seungwon Shin, and Kimin Lee, Korea Advanced Institute of Science and Technology (KAIST) Recent advancements in Large Language Models (LLMs) have established them as agentic systems capable of planning and interacting ...admin - October 14, 2025 - 5:20 pm
-
Security and Privacy Advice for UPI Users in India
Deepthi Mungara and Harshini Sri Ramulu, Paderborn University; Yasemin Acar, Paderborn University and The George Washington University Unified Payments Interface (UPI) payment systems are widely used in India and are also gaining global traction. UPI enab ...admin - October 30, 2025 - 1:44 pm
-
Watch the Watchers! On the Security Risks of Robustness-Enhancing Diffusion Models
Changjiang Li, Stony Brook University; Ren Pang, Bochuan Cao, Jinghui Chen, and Fenglong Ma, The Pennsylvania State University; Shouling Ji, Zhejiang University; Ting Wang, Stony Brook University Thanks to their remarkable denoising capabilities, diffusio ...admin - October 14, 2025 - 5:19 pm
-
DISPATCH: Unraveling Security Patches from Entangled Code Changes
complicating security patch detection, verification, and deployment. In this paper, we develop a patch ...admin - October 14, 2025 - 4:17 pm
-
Membership Inference Attacks Against Vision-Language Models
of such risks in VLMs. In this paper, we conduct the first analysis of misuse and leakage detection ...admin - October 14, 2025 - 4:42 pm
-
Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents
Avital Shafran, The Hebrew University; Roei Schuster, Wild Moose; Vitaly Shmatikov, Cornell Tech Retrieval-augmented generation (RAG) systems respond to queries by retrieving relevant documents from a knowledge database and applying an LLM to the retrieve ...admin - October 14, 2025 - 4:42 pm
-
BEAT-MEV: Epochless Approach to Batched Threshold Encryption for MEV Prevention
Jan Bormet, Sebastian Faust, Hussien Othman, and Ziyan Qu, Technische Universität Darmstadt In decentralized finance (DeFi), the public availability of pending transactions presents significant privacy concerns, enabling market manipulation through miner ...admin - October 14, 2025 - 3:54 pm
-
From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Models
beyond those in experimental datasets. In this paper, we present an in-depth evaluation of VLMs' ...admin - October 14, 2025 - 4:28 pm
-
Characterizing the MrDeepFakes Sexual Deepfake Marketplace
this paper, we systematically characterize the most prominent and mainstream marketplace, MrDeepFakes. ...admin - October 14, 2025 - 4:13 pm
-
zk-promises: Anonymous Moderation, Reputation, and Blocking from Anonymous Credentials with Callbacks
Maurice Shih, Michael Rosenberg, and Hari Kailad, University Of Maryland; Ian Miers, University of Maryland Anonymity is essential for free speech and expressing dissent, but platform moderators need ways to police bad actors. For anonymous clients, this ...admin - October 14, 2025 - 5:21 pm
-
FLOP: Breaking the Apple M3 CPU via False Load Output Predictions
Jason Kim, Jalen Chuang, and Daniel Genkin, Georgia Tech; Yuval Yarom, Ruhr University Bochum To bridge the ever-increasing gap between the fast execution speed of modern processors and the long latency of memory accesses, CPU vendors continue to introduc ...admin - October 14, 2025 - 4:28 pm
-
Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
logits-based attacks), which are usually not available in practice. In this paper, we study the vulnerability ...admin - October 14, 2025 - 5:16 pm
-
Phantom: Privacy-Preserving Deep Neural Network Model Obfuscation in Heterogeneous TEE and GPU System
Juyang Bai, Johns Hopkins University; Md Hafizul Islam Chowdhuryy, University of Central Florida; Jingtao Li, Sony AI; Fan Yao, University of Central Florida; Chaitali Chakrabarti and Deliang Fan, Arizona State University In this work, we present Phantom, ...admin - October 14, 2025 - 4:52 pm
-
Misty Registry: An Empirical Study of Flawed Domain Registry Operation
Mingming Zhang, Zhongguancun Laboratory; Yunyi Zhang, National University of Defense Technology and Tsinghua University; Baojun Liu and Haixin Duan, Tsinghua University and Zhongguancun Laboratory; Min Zhang, Fan Shi, and Chengxi Xu, National University o ...admin - October 14, 2025 - 4:43 pm
-
ChainFuzz: Exploiting Upstream Vulnerabilities in Open-Source Supply Chains
vulnerabilities. In this paper, we propose ChainFuzz, an automated approach for validating upstream vulnerabilities ...admin - October 14, 2025 - 3:49 pm
-
Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
Yining Wang, Mi Zhang, Junjie Sun, Chenyue Wang, and Min Yang, Fudan University; Hui Xue, Jialing Tao, Ranjie Duan, and Jiexi Liu, Alibaba Group Fusing visual understanding into language generation, Multi-modal Large Language Models (MLLMs) are revolution ...admin - October 14, 2025 - 4:43 pm
-
AUDIO WATERMARK: Dynamic and Harmless Watermark for Black-box Voice Dataset Copyright Protection
quality; 4) they are easily detectable due to their static backdoor patterns. In this paper, we introduce ...admin - October 14, 2025 - 3:52 pm
-
Practical Mempool Privacy via One-time Setup Batched Threshold Encryption
Arka Rai Choudhuri, Nexus; Sanjam Garg and Guru Vamsi Policharla, University of California, Berkeley; Mingyuan Wang, NYU Shanghai An important consideration with the growth of the DeFi ecosystem is the protection of clients who submit transactions to the ...admin - October 14, 2025 - 4:53 pm