conftrace_

backdoor attack

385 papers

Explore in graph

Also known as

BA

Co-occurring keywords

adversarial learning (1595) adversarial attack (1621) model security (118) data poisoning (128) neural network (6616) federated learning (1333) adversarial defense (325) poisoning attack (98) large language model (13587) neural network security (46)

Papers

CROWD: Certified Robustness via Weight Distribution for Smoothed Classifiers against Backdoor Attack EMNLP 2024
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract) AAAI 2024
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness NIPS 2024
Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks AAAI 2024
UMA: Facilitating Backdoor Scanning via Unlearning-Based Model Ablation AAAI 2024
Provable Robustness against a Union of L_0 Adversarial Attacks AAAI 2024
Data Poisoning based Backdoor Attacks to Contrastive Learning CVPR 2024
BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents ACL 2024
Optimistic Verifiable Training by Controlling Hardware Nondeterminism NIPS 2024
Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models CVPR 2024
ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger NAACL 2024
Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness in the Physical World IJCAI 2024
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning NAACL 2024
Composite Backdoor Attacks Against Large Language Models NAACL 2024
Backdoor Attacks on Multilingual Machine Translation NAACL 2024
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning CVPR 2024
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP CVPR 2024
Invariant Aggregator for Defending against Federated Backdoor Attacks AISTATS 2024
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models NAACL 2024
Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor NIPS 2024
Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning NAACL 2024
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors NAACL 2024
Data Free Backdoor Attacks NIPS 2024
DarkFed: A Data-Free Backdoor Attack in Federated Learning IJCAI 2024
Backdoor NLP Models via AI-Generated Text COLING 2024