Attack Stealthiness

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 21

All topics

Stealth Is a Relation, Not a Property: How Event Representations Create Blind Spots for Timing Attacks in Event-Based Perception
Sep 28, 2026Shoaib Ahmed Dipu, Md. Shaown Miah, Kamrul Hasan +1Attack Stealthiness Video Surveillance
Indiana University Indianapolis · Bangladesh University of Engineering and Technology · Tennessee State University
The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video Generation
Sep 7, 2026Peng Li, Qianqian Xu, Yangbangyan Jiang +2Generative Video Models Video Generation
School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence and Robotics, Hunan University, Changsha, China +1
QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models
Jul 31, 2026Xiang Chen, Yingying Zhao, Chao Li +7Attack Stealthiness
Physically Real-time Infrared Attack against Optical Flow Estimation Networks
Jul 29, 2026Shen You, Wei Jiang, Jiarui Liu +4Optical Flow Black-Box Adversarial Attacks
City University of Hong Kong Tat Chee Avenue, Kowloon, Hong Kong SAR · University of Electronic Science and Technology Chengdu, Sichuan, China · Shenzhen University Shenzhen,Guangdong,China +1
StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents
Jul 28, 2026Ads Dawson, Adrian WoodAttack Stealthiness Security Evaluation
Security Researcher, USA
Occluded Oculus: Operationalizing Stylistic Obscurement
Jul 27, 2026Robert DilworthObfuscation Attack Stealthiness
Department of Computer Science and Engineering, Mississippi State University, Mississippi State, Mississippi, USA
Transforming Keystroke Noise to Text: Self-Supervised Acoustic Eavesdropping Attacks on Keyboards
Jul 24, 2026Atsunori Okada, Akira Ito, Rei Ueno +2Keystroke Dynamics Attack Stealthiness
Tohoku University · Kyoto University · Nara Institute of Science and Technology
Proofs of Ownership for Machine Learning Models
Jun 29, 2026Ran Canetti, Shafi Goldwasser, Or ZamirDataset Ownership Verification Zero-Knowledge Proofs
Boston University · MIT · UC Berkeley +1
Agentic Knowledge Tracing: A Multi-Agent LLM Architecture for Stealth Assessment of Financial Literacy in Serious Games
Jun 24, 2026Gabriel Santos, Rita Julia, Marcelo NascimentoAgentic Learning Financial Question Answering
Federal University of Uberlˆandia Computer Science Faculty S˜ao Paulo, Brazil
Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
May 28, 2026Chia-Yi Hsu, Chia-Mu Yu, Chun-Ying Huang +1Malicious Agents Coding Agents
Department of Computer Science National Yang Ming Chiao Tung University · Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University · School of Computing Institute of Science Tokyo
The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems
May 27, 2026Nikolay Radev, Lennart Haas, Benjamin Arnav +1Sabotage Coding Agents
Passivity-based Semi-autonomous Rotational Motion Navigation for Rigid-body Networks: Stability and Human Passivity Analysis
May 23, 2026Reiji Terunuma, Yuta Nakamura, Takeshi HatanakaActive Flow Control Passive
Institute of Science Tokyo
Sample-wise Targeted Adversarial Attacks on Test-time Adaptation
May 22, 2026Phuc Duc Nguyen, Quang Duc NguyenStable Test-Time Adaptation Black-Box Adversarial Attacks
College of Computing and Data Science Nanyang Technological University Singapore
Can Quantum Federated Learning Withstand Circuit-Level Backdoors?
May 18, 2026Aakar Mathur, Mohammed Ruknuddin, Ashish GuptaFederated Learning Variational Quantum Algorithms
BITS Pilani Dubai Campus, Dubai, UAE
ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
May 9, 2026Kewei Chen, Yayu Long, Shuai Li +1Diffusion-Based Vision-Language-Actions Vision-Language Model Adaptation
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences · Chongqing School, University of Chinese Academy of Sciences · Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
May 8, 2026Zhichao Liu, Wenbo Pan, Haining Yu +3Hijacking Browser Agent
Harbin Institute of Technology · City University of Hong Kong · City University of Macau
GESR: Graph-Based Edge Semantic Reconstruction for Stealthy Communication Detection with Benign-Only Training
May 8, 2026Henghui Xu, Yuchen Zhang, Xiaobo MaGeneralist Graph Anomaly Detection Intrusion Detection
MOE Key Laboratory for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, China · Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, China · Shaanxi Province Key Laboratory of Computer Network, Xi’an Jiaotong2026 University, Xi’an, China
The Forensic Cost of Watermark Removal: From Dedicated Attacks to Image Editing
Apr 28, 2026Gautier Evennou, Ewa KijakMulti-Bit Watermarking Watermarks
IMATAG · IRISA, Univ. Rennes, INRIA, CNRS
Zero-Shot Retail Theft Detection via Orchestrated Vision Models: A Model-Agnostic, Cost-Effective Alternative to Trained Single-Model Systems
Apr 16, 2026Haileab YagersewObject Detection Vision Foundation Models
Paza AI Addis Ababa, Ethiopia
Unveiling Hidden Threats: Using Fractal Triggers to Boost Stealthiness of Distributed Backdoor Attacks in Federated Learning
Nov 12, 2025Jian Wang, Hong Shen, Chan-Tong LamClean Label Backdoor Attack Federated Learning
Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR, China · School of Cyberspace Security, Guangzhou University of Software, Guangzhou, China · School of Engineering and Technology, Central Queensland University, Australia
Random Walk Learning and the Pac-Man Attack
Aug 1, 2025Xingran Chen, Parimal Parag, Rohit Bhagat +2Decentralized Learning Bounded Adversary
Department of Electrical and Computer Engineering, Rutgers University, Piscataway Township, NJ 08854, USA · Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore, Karnataka 560012, India

Sep 28, 2026, cs.CVJ/K move · Enter open · S save

Stealth Is a Relation, Not a Property: How Event Representations Create Blind Spots for Timing Attacks in Event-Based Perception

Shoaib Ahmed Dipu, Md. Shaown Miah, Kamrul Hasan, Sayeed Shafayet Chowdhury

Indiana University Indianapolis · Bangladesh University of Engineering and Technology · Tennessee State University

Attack Stealthiness Video Surveillance Gradient-Based Attacks Blind Spots Cross-View Fusion Automatic Speech Recognition

Open paper AskPDF arXiv

An event camera produces an asynchronous stream, but what is visible in that stream depends on how a downstream consumer, such as a model or detector, processes time. The same timestamp change may leave a coarse temporal representation unchanged while changing the response of a model that preserves finer timing. We characterize this dependence as observer-relative stealth. For recorded event streams, retiming an event within its protected accumulation window leaves the accumulated integer tensor exactly unchanged. We use this exact blind space to construct Null, a gradient-guided timestamp-retiming attack, and define SC-ASR_A(tau) to measure attack success while bounding the change visible to observer A. On DVS Gesture at a 10% event budget, Null reaches 81.56 +/- 5.81% ASR on ConvSNN and 98.67 +/- 0.45% on a GRU while preserving the protected tensor exactly. On DailyDVS-200, a protocol-scale Multi-View Fusion Network variant reaches 99.28 +/- 0.11% exact-null ASR, compared with 9.70 +/- 1.06% for its matched control. In a five-attack comparison, Null is the only method with nonzero attack success at exact observer equality, reaching 81.4% on DVS Gesture and 87.35% on DailyDVS-200. We also search the same exact blind space with an independently implemented constrained projected-gradient optimizer, C-PGD. At matched victim-gradient evaluations, C-PGD reaches 84.50 +/- 2.89% ASR on DVS Gesture and 89.55 +/- 4.39% on DailyDVS-200, again with exact protected equality. Perturbations that are exactly hidden from the protected observer become visible under shifted, finer, overlapping, and randomized temporal views. Adding observer constraints reduces the real-valued blind-space fraction from 87.5% to 75.0% to 62.5%, while DVS ConvSNN ASR falls from 74.9% to 61.9% to 37.2%. These results show that stealth is not a property of the perturbation alone.

Momentum

Related topics

Latest papers 21