conftrace_
← Core AI
Artificial Intelligence › Core AI ›

AI Safety

3,026 papers

Papers per year

5
111
1031
'15
'20
'25

Papers

How Susceptible Are LLMs to Logical Fallacies? COLING 2024
Truthful High Dimensional Sparse Linear Regression NIPS 2024
Disinformation Capabilities of Large Language Models ACL 2024
Goal Alignment: Re-analyzing Value Alignment Problems Using Human-Aware AI AAAI 2024
Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method NAACL 2024
Reinforcement Learning-Driven LLM Agent for Automated Attacks on LLMs ACL 2024
On the Convergence of an Adaptive Momentum Method for Adversarial Attacks AAAI 2024
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users NIPS 2024
Navigating the OverKill in Large Language Models ACL 2024
Securing Multi-turn Conversational Language Models From Distributed Backdoor Attacks EMNLP 2024
Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context NIPS 2024
Covert Bias: The Severity of Social Views’ Unalignment in Language Models Towards Implicit and Explicit Opinion EMNLP 2024
Formal Verification of Unknown Stochastic Systems via Non-parametric Estimation AISTATS 2024
Exploring Multilingual Concepts of Human Values in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages? EMNLP 2024
Does Few-Shot Learning Suffer from Backdoor Attacks? AAAI 2024
Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic ACL 2024
Adversarial Math Word Problem Generation EMNLP 2024
DeepSaDe: Learning Neural Networks That Guarantee Domain Constraint Satisfaction AAAI 2024
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models EMNLP 2024
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract) AAAI 2024
Fight Back Against Jailbreaking via Prompt Adversarial Tuning NIPS 2024
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning CVPR 2024
Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs NAACL 2024
Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications ACL 2024
Conditional Backdoor Attack via JPEG Compression AAAI 2024