Skip to content
conftrace_

Tsung-Yi Ho

27 papers · 2020–2026 · 8 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 ↓
+12 more ↓ πŸ—ΊοΈ Taxonomy Completionist (43) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
πŸ† Grand Slam πŸ”¬ Deep Specialist (10) 🧬 Topic Evolution πŸ‘‘ Triple Crown 🀝 Dynamic Duo (20) ⚑ Prolific Year Β· Prolific πŸ”₯ Unstoppable Β· Bronze ❓ The Questioner πŸ’Ž Century Club Β· Bronze πŸš€ Conference Pioneer 🌈 Renaissance Researcher (6) πŸ—ƒοΈ Keyword Collector (117)

Venues

AAAI (7) NeurIPS (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

Machine Learning (21) Artificial Intelligence (15) Core AI (15) Deep Learning (13) Learning Types Β· Machine Learning (11) Application Areas (8) Models (6) Learning Types Β· Deep Learning (5) Computer Vision (4) Optimization & Theory (4) Natural Language Processing (2) Reinforcement Learning (2) Analysis (2) Applications (2) Architectures (2)

Keywords

adversarial attack (6) jailbreak attack (5) large language model (5) adversarial example (4) backdoor attack (4) diffusion model (4) adversarial robustness (3) adversarial defense (3) generative model (3) safety alignment (3) representation similarity (2) model robustness (2) object detection (2) robustness evaluation (2) adversarial learning (2) deep neural network (2) transfer learning (2) policy learning (2) prompt engineering (1) self-supervised learning (1)

Papers

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