← Authors

Dawn Song

103 papers · 2009–2026 · 16 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (14) 🐝 Cross-Pollinator (15) πŸƒ Academic Marathon (16) 🌍 Conference Polyglot (16) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌟 Keyword Trendsetter Combo (4) 🏠 Conference Loyalist (20) πŸ‘₯ Mega-Team (34) 🀝 Dynamic Duo (32) πŸ”¬ Deep Specialist (16) 🧬 Topic Evolution πŸ† Keyword Champion πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ“ˆ Trend Setter πŸ’Ž Century Club (102) ⚑ Prolific Year (8) πŸ”₯ Unstoppable (8) ❓ The Questioner (2) πŸ—ƒοΈ Keyword Collector (289) πŸš€ Conference Pioneer

Conferences

ICLR (24) NIPS (20) ICML (17) EMNLP (10) CVPR (8) ACL (6) IJCAI (4) AAAI (2) AISTATS (2) ECCV (2) ICCV (2) IJCNLP (2) AACL (1) COLING (1) OSDI (1) UAI (1)

Top co-authors

Bo Li (32) Dan Hendrycks (14) Xinyun Chen (13) Ruoxi Jia (12) Chenguang Wang (11) Xuandong Zhao (9) Chaowei Xiao (8) Jacob Steinhardt (8) Mantas Mazeika (8) Chang Liu (6)

Research topics

Differential Privacy (1) Privacy (1)

Keywords

adversarial example (8) backdoor attack (6) program synthesis (6) adversarial attack (6) language model (5) adversarial learning (5) adversarial robustness (5) neural network (5) federated learning (5) large language model (5) transfer learning (5) zero-shot learning (4) differential privacy (4) attention mechanism (4) code generation (4) adversarial training (4) safety alignment (3) diffusion model (3) data augmentation (3) anomaly detection (3)

Papers

Can Editing LLMs Inject Harm? AAAI 2026
GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning ICML 2025
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025
AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents EMNLP 2025
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 IJCNLP 2025
CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification AAAI 2025
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 AACL 2025
COSMIC: Generalized Refusal Direction Identification in LLM Activations ACL 2025
MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models ACL 2025
Position: Formal Mathematical Reasoningβ€”A New Frontier in AI ICML 2025
Multimodal Situational Safety ICLR 2025
Tamper-Resistant Safeguards for Open-Weight LLMs ICLR 2025
Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI ICML 2025
AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories ICLR 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models ICLR 2025
An Undetectable Watermark for Generative Image Models ICLR 2025
Data Shapley in One Training Run ICLR 2025
Capturing the Temporal Dependence of Training Data Influence ICLR 2025
Position: Political Neutrality in AI Is Impossible β€” But Here Is How to Approximate It ICML 2025
Improving LLM Safety Alignment with Dual-Objective Optimization ICML 2025
Agent Instructs Large Language Models to be General Zero-Shot Reasoners ICML 2024
GRATH: Gradual Self-Truthifying for Large Language Models ICML 2024
Position: Evolving AI Collectives Enhance Human Diversity and Enable Self-Regulation ICML 2024
Position: On the Societal Impact of Open Foundation Models ICML 2024
C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models ICML 2024
Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning ACL 2024
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content ICML 2024
SHINE: Shielding Backdoors in Deep Reinforcement Learning ICML 2024
Hidden Persuaders: LLMs’ Political Leaning and Their Influence on Voters EMNLP 2024
Data Free Backdoor Attacks NIPS 2024
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models NIPS 2024
RedCode: Risky Code Execution and Generation Benchmark for Code Agents NIPS 2024
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases NIPS 2024
GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration NIPS 2024
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models EMNLP 2024
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression ICML 2024
Effective and Efficient Federated Tree Learning on Hybrid Data ICLR 2024
The False Promise of Imitating Proprietary Language Models ICLR 2024
Secure Federated Correlation Test and Entropy Estimation ICML 2023
Adversarial Collaborative Learning on Non-IID Features ICML 2023
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models NIPS 2023
BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning NIPS 2023
Byzantine-Robust Federated Learning with Optimal Statistical Rates AISTATS 2023
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification NIPS 2023
TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets CVPR 2023
DensePure: Understanding Diffusion Models for Adversarial Robustness ICLR 2023
DeepStruct: Pretraining of Language Models for Structure Prediction ACL 2022
How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios NIPS 2022
Forecasting Future World Events With Neural Networks NIPS 2022
Joint Language Semantic and Structure Embedding for Knowledge Graph Completion COLING 2022
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures CVPR 2022
IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models EMNLP 2022
Benchmarking Language Models for Code Syntax Understanding EMNLP 2022
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion EMNLP 2022
Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space ICLR 2022
Scaling Out-of-Distribution Detection for Real-World Settings ICML 2022
Perturbation type categorization for multiple adversarial perturbation robustness UAI 2022
Natural Adversarial Examples CVPR 2021
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning IJCAI 2021
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization ICCV 2021
Grounded Graph Decoding improves Compositional Generalization in Question Answering EMNLP 2021
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation EMNLP 2021
Practical One-Shot Federated Learning for Cross-Silo Setting IJCAI 2021
Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification? CVPR 2021
Model-Contrastive Federated Learning CVPR 2021
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models ICML 2021
Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams NIPS 2021
Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages NIPS 2021
PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context ACL 2021
Measuring Massive Multitask Language Understanding ICLR 2021
Aligning AI With Shared Human Values ICLR 2021
PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context IJCNLP 2021
Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis NIPS 2020
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks CVPR 2020
Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension ICLR 2020
Imitation Attacks and Defenses for Black-box Machine Translation Systems EMNLP 2020
Towards practical differentially private causal graph discovery NIPS 2020
Pretrained Transformers Improve Out-of-Distribution Robustness ACL 2020
Robust anomaly detection and backdoor attack detection via differential privacy ICLR 2020
Compositional Generalization via Neural-Symbolic Stack Machines NIPS 2020
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty NIPS 2019
Synthetic Datasets for Neural Program Synthesis ICLR 2019
Characterizing Audio Adversarial Examples Using Temporal Dependency ICLR 2019
GamePad: A Learning Environment for Theorem Proving ICLR 2019
Execution-Guided Neural Program Synthesis ICLR 2019
AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos ICCV 2019
Towards Efficient Data Valuation Based on the Shapley Value AISTATS 2019
Parametrized Hierarchical Procedures for Neural Programming ICLR 2018
Robust Physical-World Attacks on Deep Learning Visual Classification CVPR 2018
Fooling Vision and Language Models Despite Localization and Attention Mechanism CVPR 2018
Improving Neural Program Synthesis with Inferred Execution Traces NIPS 2018
Towards Synthesizing Complex Programs From Input-Output Examples ICLR 2018
Spatially Transformed Adversarial Examples ICLR 2018
Practical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms ECCV 2018
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality ICLR 2018
Tree-to-tree Neural Networks for Program Translation NIPS 2018
Curriculum Adversarial Training IJCAI 2018
Generating Adversarial Examples with Adversarial Networks IJCAI 2018
Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation ECCV 2018
Decision Boundary Analysis of Adversarial Examples ICLR 2018
Latent Attention For If-Then Program Synthesis NIPS 2016
Code-Pointer Integrity OSDI 2014
Tracking Dynamic Sources of Malicious Activity at Internet Scale NIPS 2009