conftrace_
← Authors

Tsung-Yi Ho

27 papers · 2020–2026 · 8 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+14 more ↓ πŸ—ΊοΈ Taxonomy Completionist (10) 🧭 Keyword Pioneer πŸŒ‰ Interdisciplinary Bridge 🌈 Renaissance Researcher (5) 🐣 Hot Topic Early Bird
🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (10) 🀝 Dynamic Duo (19) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (10) 🧬 Topic Evolution ⚑ Prolific Year (6) πŸ”₯ Unstoppable (6) ❓ The Questioner πŸ’Ž Century Club (25) πŸ—ƒοΈ Keyword Collector (102) πŸš€ Conference Pioneer

Conferences

AAAI (7) NIPS (6) ICML (4) CVPR (3) ICLR (3) ACL (2) IJCAI (1) MICCAI (1)

Top co-authors

Pin-Yu Chen (20) Lei Hsiung (6) Sheng-Yen Chou (4) Yun-Yun Tsai (3) Xiaomeng Hu (3) Qiang Xu (2) ZAITANG LI (2) Tzungyu Tsai (2) Xiaokang Chen (2) Daoguang Zan (2)

Research topics

Robotics (1) Security & Privacy (1) Privacy (1)

Keywords

adversarial attack (6) jailbreak attack (5) large language model (5) diffusion model (4) backdoor attack (3) generative model (3) adversarial robustness (3) adversarial example (3) adversarial defense (3) safety alignment (3) model robustness (2) object detection (2) policy learning (2) deep neural network (2) robustness evaluation (2) multimodal learning (1) model evaluation (1) model security (1) prompt engineering (1) multi-agent reinforcement learning (1)

Papers

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026 KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits AAAI 2026 Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models AAAI 2025 Retention Score: Quantifying Jailbreak Risks for Vision Language Models AAAI 2025 Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks ACL 2025 Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning ICML 2024 GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models NIPS 2024 Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift AAAI 2024 NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes NIPS 2024 MMA-Diffusion: MultiModal Attack on Diffusion Models CVPR 2024 Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes NIPS 2024 The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models ICLR 2024 Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective ICLR 2024 AutoVP: An Automated Visual Prompting Framework and Benchmark ICLR 2024 Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis MICCAI 2024 Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations CVPR 2023 RADAR: Robust AI-Text Detection via Adversarial Learning NIPS 2023 VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models NIPS 2023 NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration AAAI 2023 Uncovering and Quantifying Social Biases in Code Generation NIPS 2023 How to Backdoor Diffusion Models? CVPR 2023 CARBEN: Composite Adversarial Robustness Benchmark IJCAI 2022 Parallel Droplet Control in MEDA Biochips using Multi-Agent Reinforcement Learning ICML 2021 Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources ICML 2020 Adaptive Droplet Routing in Digital Microfluidic Biochips Using Deep Reinforcement Learning ICML 2020 Beyond Digital Domain: Fooling Deep Learning Based Recognition System in Physical World AAAI 2020 Robust Adversarial Objects against Deep Learning Models AAAI 2020