conftrace_

backdoor injection

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (2) client embedding (1) byzantine-resistant aggregation (1) logit anchoring (1) malicious client detection (1) adversarial weight perturbation (1) trojan attack (1) large language model (1) byzantine resilience (1) model consistency (1)

Papers

Protecting Model Adaptation from Trojans in the Unlabeled Data AAAI 2025 Enhancing Byzantine-Resistant Aggregations with Client Embedding EMNLP 2024 Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections NAACL 2024 How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data ICLR 2022