Search results
-
Expert Insights into Advanced Persistent Threats: Analysis, Attribution, and Challenges
Aakanksha Saha, Technische Universität Wien; James Mattei, Tufts University; Jorge Blasco, Universidad Politécnica de Madrid; Lorenzo Cavallaro, University College London; Daniel Votipka, Tufts University; Martina Lindorfer, Technische Universität Wien Ad ...admin - October 14, 2025 - 4:20 pm
-
Tracking the Takes and Trajectories of English-Language News Narratives across Trustworthy and Worrisome Websites
Hans W. A. Hanley, Emily Okabe, and Zakir Durumeric, Stanford University Understanding how misleading and outright false information enters and spreads within news ecosystems remains a difficult challenge that requires tracking how stories spread across t ...admin - October 14, 2025 - 5:16 pm
-
AKMA+: Security and Privacy-Enhanced and Standard-Compatible AKMA for 5G Communication
Yang Yang and Guomin Yang, Singapore Management University; Yingjiu Li, University of Oregon; Minming Huang, Singapore Management University; Zilin Shen and Imtiaz Karim, Purdue University; Ralf Sasse and David Basin, ETH Zurich; Elisa Bertino, Purdue Uni ...admin - October 14, 2025 - 3:48 pm
-
SoK: On Gradient Leakage in Federated Learning
Jiacheng Du and Jiahui Hu, The State Key Laboratory of Blockchain and Data Security, Zhejiang University, P. R. China; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, P. R. China; and College of Computer Science and Electroni ...admin - October 14, 2025 - 5:08 pm
-
AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
Jiate Li and Binghui Wang, Illinois Institute of Technology Graph neural networks (GNNs) achieve the state-of-the-art on graph-relevant tasks such as node and graph classification. However, recent works show GNNs are vulnerable to adversarial perturbation ...admin - October 14, 2025 - 3:45 pm
-
zkGPT: An Efficient Non-interactive Zero-knowledge Proof Framework for LLM Inference
tremendous overhead. To address this issue, this paper introduces several new techniques. We propose new ...admin - October 14, 2025 - 5:21 pm
-
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes ...admin - October 30, 2025 - 3:00 pm
-
Pretender: Universal Active Defense against Diffusion Finetuning Attacks
Zekun Sun and Zijian Liu, Shanghai Jiao Tong University; Shouling Ji, Zhejiang University; Chenhao Lin, Xi'an Jiaotong University; Na Ruan, Shanghai Jiao Tong University The proliferation of Diffusion Models (DMs) has marked a significant advancement ...admin - October 14, 2025 - 4:53 pm
-
Waltzz: WebAssembly Runtime Fuzzing with Stack-Invariant Transformation
Lingming Zhang, Zhejiang University; Binbin Zhao, Zhejiang University, Georgia Institute of Technology, and Engineering Research Center of Blockchain Application, Supervision And Management (Southeast University), Ministry of Education; Jiacheng Xu and Pe ...admin - October 30, 2025 - 1:56 pm
-
On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
such harmful capabilities. In this paper, we investigate the proactive generation of unsafe images from ...admin - October 14, 2025 - 4:48 pm
-
MBFuzzer: A Multi-Party Protocol Fuzzer for MQTT Brokers
this paper, we design a black-box fuzzing approach, MBFuzzer, for brokers to address the above ...admin - October 14, 2025 - 4:42 pm
-
Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications
outputs known as "hallucinations'' that deviate from factual knowledge. In this paper, we ...admin - October 14, 2025 - 5:13 pm
-
Email Spoofing with SMTP Smuggling: How the Shared Email Infrastructures Magnify this Vulnerability
evaluated and the effectiveness of the community's mitigation strategies is yet unknown. In this paper ...admin - October 14, 2025 - 4:20 pm
-
How Researchers De-Identify Data in Practice
Wentao Guo, University of Maryland; Paige Pepitone, NORC at the University of Chicago; Adam J. Aviv, The George Washington University; Michelle L. Mazurek, University of Maryland Human-subjects researchers are increasingly expected to de-identify and publ ...admin - October 14, 2025 - 4:31 pm
-
VoiceWukong: Benchmarking Deepfake Voice Detection
Ziwei Yan, Yanjie Zhao, and Haoyu Wang, Huazhong University of Science and Technology With the rapid advancement of technologies like text-to-speech (TTS) and voice conversion (VC), detecting deepfake voices has become increasingly crucial. However, both ...admin - October 14, 2025 - 5:19 pm
-
Secure Information Embedding in Forensic 3D Fingerprinting
Canran Wang, Jinwen Wang, Mi Zhou, Vinh Pham, Senyue Hao, Chao Zhou, Ning Zhang, and Netanel Raviv, Washington University in St. Louis Printer fingerprinting techniques have long played a critical role in forensic applications, including the tracking of c ...admin - October 14, 2025 - 5:04 pm
-
ImpROV: Measurement and Practical Mitigation of Collateral Damage in RPKI Route Origin Validation
paper, we conduct the first comprehensive study to measure the extent of collateral damage in the real ...admin - October 14, 2025 - 4:32 pm
-
Persistent Backdoor Attacks in Continual Learning
Zhen Guo, Abhinav Kumar, and Reza Tourani, Saint Louis University Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critic ...admin - October 14, 2025 - 4:53 pm
-
SoK: Towards Effective Automated Vulnerability Repair
Ying Li, University of California, Los Angeles; Faysal Hossain Shezan, University of Texas at Arlington; Bomin Wei, University of California, Los Angeles; Gang Wang, University of Illinois Urbana-Champaign; Yuan Tian, University of California, Los Angeles ...admin - October 14, 2025 - 5:12 pm
-
Analyzing the AI Nudification Application Ecosystem
face of modern (and future) AI-based nudification applications. redContent warning: This paper includes ... imagery (SNEACI). This paper also includes an artistic rendering of a user interface for such an ...admin - October 14, 2025 - 3:48 pm
-
Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
Zihang Xiang, KAUST; Tianhao Wang, University of Virginia; Di Wang, KAUST Auditing algorithms' privacy typically involves simulating a game-based protocol that determines which of two adjacent datasets was the original input. Traditional approaches r ...admin - October 14, 2025 - 4:58 pm
-
We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs
Texas at San Antonio Distinguished Paper Award Winner The reliance of popular programming languages such ... a critical threat to the integrity of the software supply chain. This paper conducts a rigorous and ...admin - October 14, 2025 - 5:19 pm
-
Following Devils' Footprint: Towards Real-time Detection of Price Manipulation Attacks
Bosi Zhang, Huazhong University of Science and Technology; Ningyu He, The Hong Kong Polytechnic University; Xiaohui Hu, Kai Ma, and Haoyu Wang, Huazhong University of Science and Technology Price manipulation attack is one of the notorious threats in dece ...admin - October 14, 2025 - 4:28 pm
-
GNSS-WASP: GNSS Wide Area SPoofing
Switzerland In this paper, we propose GNSS-WASP, a novel wide-area spoofing attack carried by a constellation ...admin - October 14, 2025 - 4:31 pm
-
Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI
attention has been given to attacks targeting deep learning models. In this paper, we introduce the use of ...admin - October 14, 2025 - 4:14 pm