Skip to content
conftrace_

inference-time defense

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) text generation (2) adversarial robustness (2) harmful queries (1) backdoor attack mitigation (1) semantic space control (1) confidence drift (1) fine-tuning as a service (1) belief stability (1) safety context amnesia (1)

Papers

Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models AAAI 2026 Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations EACL 2026 Mitigating Safety Context Amnesia in Multimodal Reasoning Models via Intent-Guided Safety Reasoning ACL 2026 Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language Model AAAI 2026 SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs AAAI 2026 When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure ACL 2026 CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models EMNLP 2024 TTTS: Tree Test Time Simulation for Enhancing Decision Tree Robustness against Adversarial Examples AAAI 2024