conftrace_

backdoor attack

476 papers

Explore in graph

Also known as

BA

Co-occurring keywords · papers mentioning both

adversarial learning (111) adversarial attack (81) model security (56) data poisoning (56) neural network (53) federated learning (47) adversarial defense (39) large language model (39) poisoning attack (38) deep neural network (36)

Papers

Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models AAAI 2024 Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World CVPR 2024 Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection ICLR 2024 Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models NeurIPS 2024 Progressive Poisoned Data Isolation for Training-Time Backdoor Defense AAAI 2024 Provable Robustness against a Union of L_0 Adversarial Attacks AAAI 2024 Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective AAAI 2024 Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective ICLR 2024 Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain ICLR 2024 Safe and Robust Watermark Injection with a Single OoD Image ICLR 2024 Securing Multi-turn Conversational Language Models From Distributed Backdoor Attacks EMNLP 2024 Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment CVPR 2024 SHINE: Shielding Backdoors in Deep Reinforcement Learning ICML 2024 Shortcuts Arising from Contrast: Towards Effective and Lightweight Clean-Label Attacks in Prompt-Based Learning EMNLP 2024 SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents NeurIPS 2024 T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models ECCV 2024 Temporal-Distributed Backdoor Attack against Video Based Action Recognition AAAI 2024 TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors ICML 2024 The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline ICML 2024 Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features ICLR 2024 Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors NAACL 2024 UMA: Facilitating Backdoor Scanning via Unlearning-Based Model Ablation AAAI 2024 Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense NeurIPS 2024 Unelicitable Backdoors via Cryptographic Transformer Circuits NeurIPS 2024 Universal Backdoor Attacks ICLR 2024