TPAMI 2026 papers on Adversarial robustness and security
30 of the 880 papers published in TPAMI 2026 (3.4%) are on Adversarial robustness and security, compared with 3.0% at TPAMI 2025. They fall into 4 topics.
See TPAMI 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Black-box and transfer attacks · 11 papers
- Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models (8 citations)
- Box-Free Model Watermarks are Prone to Black-Box Removal Attacks (7 citations)
- Robust Adaptation of Foundation Models With Black-Box Visual Prompting (4 citations)
- Seeking Flat Minima Over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation (3 citations)
- S 4 ST: A Strong, Self-Transferable, faSt, and Simple Scale Transformation for Data-Free Transferable Targeted Attack (2 citations)
- SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack Against No-Reference Image Quality Assessment Models (1 citation)
- AdvDiffusion: Adversarial Patches Generation for Face Recognition With High Transferability in Physical Domain
- ATR-UAP: Enhancing the Transferability of Data-Free Universal Adversarial Perturbation via Adaptive Truncated Ratio Maximization
- Enhancing Adversarial Transferability With Cost-Efficient Landscape Flattening
- Towards Transferable Black-Box Attack via Minimizing Maximum Model Discrepancy
- On the Adversarial Transferability of Generalized “Skip Connections”
Attacks on text and graphs · 10 papers
- Active Adversarial Noise Suppression for Image Forgery Localization (4 citations)
- Exploring Security Vulnerabilities in Multilingual Speech Translation Systems via Deceptive Inputs (4 citations)
- Out-of-Distribution-Resistant Evaluations for Explanations of Graph Neural Networks (1 citation)
- A Diffusion Prior-based Framework for Imperceptible and Flexible Unrestricted Adversarial Attacks
- Advancing Zero-Shot Adversarial Robust Fairness: Theory and Algorithm
- Complementary Text-Guided Attention for Zero-Shot Adversarial Robustness
- Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models
- LLM-Agnostic Semantic Representation Attack
- NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
- ABIGX: A Unified Framework for Explainable Fault Detection and Classification
Certified and empirical robustness · 7 papers
- Robustness of SAM: Segment Anything Under Corruptions and Beyond (42 citations)
- Improving Viewpoint Robustness for Visual Recognition via Adversarial Training (9 citations)
- CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration (6 citations)
- Allies Teach Better Than Enemies: Inverse Adversaries for Robust Knowledge Distillation (3 citations)
- Strength-Adaptive Adversarial Training (3 citations)
- Deep Supervised Adversarial Robust Hashing for Retrieval (1 citation)
- Adversarial Purification by Consistency-Aware Latent Space Optimization on Data Manifolds
