phenomenon · first seen 5 Oct 2026
adversarial perturbation
Also: adversarial attack, adversarial attack on perception, adversarial attack on object detection
Small input modifications crafted to cause a machine learning model to make incorrect predictions.
Mentions per week
PapersCodeDiscussion
Rank 73 on 16 Nov 2026 · 8 mentions in 28 days · 8 independent groups · papers · first seen 6 weeks ago · acceleration +1.95
Earliest sources
- Certification of Real Images through Calibrated Content AuthenticationPapers · 5 Oct 2026 · Sarim Hashmi, Abdelrahman Elsayed, Mohammed Talha Alam, Samuele Poppi, Nils Luka…
- VCR-Bench: A Modular Open-Source Benchmark for Video Classification RobustnessPapers · 6 Oct 2026 · Maksim Plinskiy, Aleksandr Gushchin, Sergey Lavrushkin, Dmitriy S. Vatolin, Anas…
- BRANCH: Bypassing Multi-Scanner AI GuardrailsPapers · 7 Oct 2026 · William Hackett, Peter Garraghan
- Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive EncodersPapers · 8 Oct 2026 · Tao Yang, Jianying Zhou
- LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity CollapsePapers · 9 Oct 2026 · Boheng Li, Yueming Xing, Yiming Li, Jie Zhang, Tianwei Zhang
- Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological ImagingPapers · 11 Oct 2026 · Tristan Malatyński, Joanna Jaworek-Korjakowska
Latest sources
- STA: A Split Temporal Adversary Method for Evaluating Robustness of Multimodal RL-based Driving PoliciesPapers · 16 Nov 2026 · Shenghao Xiong, Xiaolin Chang
- GPromptShield: Elevating Resilience in Graph Prompt Tuning against Adversarial AttacksPapers · 16 Nov 2026 · Shuhan Song, Ping Li, Ming Dun, Maolei Huang, Huawei Cao, Xiaochun Ye
- Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous VehiclesPapers · 12 Nov 2026 · Han Wu, Alex Chan, Ekin Can Erkus, Tousif Rahman, Rishad Shafik
- GARD: Gradient-Guided Adversarial Representation Defense against Backdoors in Multimodal Contrastive Learning ModelsPapers · 10 Nov 2026 · Yuhong Wang, Yujun Cai, Lei Feng, Songze Li
- Query-Only Prompt-Agnostic Attacks on Visual In-Context LearningPapers · 8 Nov 2026 · Xiao Hu, Muhammad Ibrahim, Hao Wen, Pin-Yu Chen, Jianliang Wu, Antonio Bianchi
- VIPA: View-Invariant Projector-Based Adversarial AttackPapers · 5 Nov 2026 · Jiyu Han, Qingyue Deng, Bingyao Huang
- Detect, Repair and Audit: A Hierarchical Multi-Agent Defense Against Adversarial Attacks in Energy ForecastingPapers · 2 Nov 2026 · Zewei Shi, Ruoxi Sun, Minhui Xue, Feng Liu, Hua Ma, Xingliang Yuan, Surya Nepal
- Attack logics, not outputs: Concept-based Property Attacks for Shortcut Elimination in Neural NetworksPapers · 26 Oct 2026 · Raik Dankworth, Felix Mächtle, Thomas Eisenbarth, Gesina Schwalbe
- Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node AttackPapers · 19 Oct 2026 · Yuyang Zhang, Yihui Jin, Kangjie Chen, Leyang Wu, Run Wang
- GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue ManipulationPapers · 14 Oct 2026 · Yixin Wu, Mingjie Li, Yun Shen, Michael Backes, Yang Zhang
- Adversarial Robustness of Camera-Radar Sensor Fusion for Autonomous DrivingPapers · 12 Oct 2026 · Ce Zhou, Yubo Wu, Khang Nguyen, Liyang Xiao, Thomas Hou, Qiben Yan
- Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological ImagingPapers · 11 Oct 2026 · Tristan Malatyński, Joanna Jaworek-Korjakowska