Ihsen Alouani

5 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

CVPR (3) EMNLP (1) WACV (1)

Top co-authors

Nael Abu-Ghazaleh (3) Quazi Mishkatul Alam (2) Bilel Tarchoun (2) Yue Dong (1) Muhammad Shafique (1) Jeonghwan Park (1) Pedram Zaree (1) Mohamed Ali Mahjoub (1) Ruitian Ding (1) Md Abdullah Al Mamun (1)

Research topics

Artificial Intelligence (5) Deep Learning (5) Core AI · Artificial Intelligence (5) Learning Types · Deep Learning (5) Machine Learning (4) Learning Types · Machine Learning (4) Computer Vision (3) Analysis (2) Computer Science (1) Applications (1) Core AI · Computer Vision (1) Processing (1)

Keywords

adversarial attack (4) adversarial patch (3) object detection (3) attention mechanism (1) safety alignment (1) person detection (1) black-box attack (1) adversarial defense (1) generative adversarial network (1) jailbreak attack (1) query-based attack (1) llm safety (1) entropy analysis (1) image recovery (1) adversarial attack detection (1) deformable transformer (1) physical attack (1) attention manipulation (1) patch localization (1) yolo detector (1)

Papers

Adversarial Attention Deficit: Fooling Deformable Vision Transformers with Collaborative Adversarial Patches WACV 2025 Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025 Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis CVPR 2025 DAP: A Dynamic Adversarial Patch for Evading Person Detectors CVPR 2024 Jedi: Entropy-Based Localization and Removal of Adversarial Patches CVPR 2023