conftrace_

backdoor

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

fine tuning (2) insecure code (1) motivation (1) predict (1) mixup (1) fine-tuning defense (1) resilient backdoors (1) stealthiness (1) activation drift (1) layer-wise correction (1)

Papers

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization ICML 2025 Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs ICML 2025 MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges ICML 2025 Augmented Neural Fine-tuning for Efficient Backdoor Purification ECCV 2024 Flatness-aware Sequential Learning Generates Resilient Backdoors ECCV 2024 Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation ICML 2024