Skip to content
conftrace_

black-box defense

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (3) adversarial defense (2) backdoor defense (2) subgraph sampling (1) parameter adaptation (1) perturbation-based method (1) defense distillation (1) large language model (1) graph neural network (1) alignment mechanism (1)

Papers

Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms ACL 2026 GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models IJCAI 2025 Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models ICLR 2025 SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification NeurIPS 2024 SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency ICLR 2023 Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks COLING 2022