adversarial examples
Adversarial examples are inputs intentionally designed to confuse or mislead AI models by exploiting their vulnerabilities, highlighting the importance of robustness in machine learning systems.
- Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies
- Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
- Attention! Your Vision Language Model Could Be Maliciously Manipulated
- Boosting Adversarial Transferability with Spatial Adversarial Alignment
- Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection
- Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
- Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations
- DiffBreak: Is Diffusion-Based Purification Robust?
- Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts
- E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
- Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
- Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models
- HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
- Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
- Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
- Scaling Data-Driven Probabilistic Robustness Analysis for Semantic Segmentation Neural Networks
- Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models
- Towards Irreversible Attack: Fooling Scene Text Recognition via Multi-Population Coevolution Search
- TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks
- Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2