Skip to content
conftrace_

Xiangyu Qi

14 papers · 2021–2025 · 7 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+8 more ↓ 🐣 Hot Topic Early Bird 🌍 Conference Polyglot Β· Silver πŸ—ΊοΈ Taxonomy Completionist (18) πŸ‘₯ Mega-Team Β· Squad πŸ† Grand Slam
πŸ”¬ Deep Specialist (11) πŸ‘₯ Mega-Team Β· Squad 🧭 Keyword Pioneer πŸ† Grand Slam ⚑ Prolific Year Β· Productive πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze πŸ—ƒοΈ Keyword Collector (58)

Venues

ICLR (6) ICML (3) AAAI (1) ACL (1) CVPR (1) NAACL (1) NeurIPS (1)

Top co-authors

Prateek Mittal (9) Tinghao Xie (7) Peter Henderson (6) Yangsibo Huang (3) Kaixuan Huang (3) Bo Li (3) Boyi Wei (3) Pin-Yu Chen (2) Mengdi Wang (2) Yiming Li (2)

Research topics

Artificial Intelligence (12) Core AI (12) Machine Learning (11) Application Areas (7) Learning Types Β· Machine Learning (4) Deep Learning (3) Optimization & Theory (2) Architectures (1) Learning Types Β· Deep Learning (1) Models (1)

Keywords

adversarial attack (5) safety alignment (4) adversarial robustness (3) large language model (3) model robustness (2) harmful content (2) deep neural network (2) safety guardrail (2) jailbreak attack (2) neural network (2) fine-tuning attack (2) deep learning (2) adversarial defense (2) ai safety (1) prompt engineering (1) responsible ai (1) data poisoning (1) model safety (1) backdoor attack (1) adversarial training (1)

Papers

Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks ACL 2025 Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability NAACL 2025 On Evaluating the Durability of Safeguards for Open-Weight LLMs ICLR 2025 Safety Alignment Should be Made More Than Just a Few Tokens Deep ICLR 2025 SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal ICLR 2025 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications ICML 2024 BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NeurIPS 2024 BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection ICLR 2024 Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! ICLR 2024 Visual Adversarial Examples Jailbreak Aligned Large Language Models AAAI 2024 Revisiting the Assumption of Latent Separability for Backdoor Defenses ICLR 2023 Uncovering Adversarial Risks of Test-Time Adaptation ICML 2023 Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks CVPR 2022 Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks ICML 2021