← Authors

Kaidi Xu

45 papers · 2019–2026 · 13 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (6) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (12) 🐝 Cross-Pollinator (8) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (10) 🧭 Keyword Pioneer πŸ† Grand Slam πŸ‘‘ Triple Crown 🀝 Dynamic Duo (15) πŸ‘₯ Mega-Team (71) πŸ”¬ Deep Specialist (10) 🧬 Topic Evolution ⚑ Prolific Year (14) πŸ—ƒοΈ Keyword Collector (161) πŸ’Ž Century Club (42) πŸ”₯ Unstoppable (7) ❓ The Questioner (4)

Conferences

NIPS (8) ICML (6) ACL (4) CVPR (4) ICCV (4) ICLR (4) AAAI (3) EMNLP (3) NAACL (3) ECCV (2) IJCAI (2) EACL (1) RSS (1)

Top co-authors

Jinhao Duan (17) Xue Lin (9) Tianlong Chen (9) Huan Zhang (9) Sijia Liu (8) Bhavya Kailkhura (8) Xiaoshuang Shi (8) Shiqi Wang (7) Hao Cheng (7) Lichao Sun (6)

Research topics

Systems (1) Applications (1) Privacy (1) Probability (1)

Keywords

large language model (9) adversarial attack (9) neural network verification (5) adversarial robustness (4) uncertainty quantification (4) adversarial training (4) image generation (3) zeroth-order optimization (3) diffusion model (3) conformal prediction (3) branch and bound (3) evasion attack (2) prediction set (2) privacy protection (2) black-box attack (2) benchmark evaluation (2) mixed integer programming (2) black-box optimization (2) strategic reasoning (2) adversarial perturbation (2)

Papers

Dialogue is Better Than Monologue: Instructing Meidcal LLMs via Strategic Conversations EACL 2026
COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees AAAI 2026
Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions AAAI 2026
GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing NAACL 2025
Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach ICML 2025
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models EMNLP 2025
Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs EMNLP 2025
SConU: Selective Conformal Uncertainty in Large Language Models ACL 2025
DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation ACL 2025
TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention ICCV 2025
DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization NAACL 2025
Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models CVPR 2025
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression ICML 2024
Dynamic Adversarial Attacks on Autonomous Driving Systems RSS 2024
GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations NIPS 2024
NN4SysBench: Characterizing Neural Network Verification for Computer Systems NIPS 2024
Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise AAAI 2024
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models ACL 2024
Reinforcement Learning-Driven LLM Agent for Automated Attacks on LLMs ACL 2024
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion? CVPR 2024
ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models CVPR 2024
Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Models ECCV 2024
ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees EMNLP 2024
ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models NAACL 2024
Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024
An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization ICLR 2024
Are Diffusion Models Vulnerable to Membership Inference Attacks? ICML 2023
Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack ICCV 2023
Improve Video Representation with Temporal Adversarial Augmentation IJCAI 2023
Toward Robust Spiking Neural Network Against Adversarial Perturbation NIPS 2022
General Cutting Planes for Bound-Propagation-Based Neural Network Verification NIPS 2022
A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks ICML 2022
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification NIPS 2021
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning ICLR 2021
Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers ICLR 2021
ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers NIPS 2021
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks ICML 2020
Adversarial T-shirt! Evading Person Detectors in A Physical World ECCV 2020
Light-weight Calibrator: A Separable Component for Unsupervised Domain Adaptation CVPR 2020
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond NIPS 2020
Structured Adversarial Attack: Towards General Implementation and Better Interpretability ICLR 2019
ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization NIPS 2019
On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method ICCV 2019
Adversarial Robustness vs. Model Compression, or Both? ICCV 2019
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective IJCAI 2019