Dawn Song

34

Papers

116

Total Citations

Papers (34)

Latent Attention For If-Then Program Synthesis

NeurIPS 2016arXiv

Data Shapley in One Training Run

Position: Evolving AI Collectives Enhance Human Diversity and Enable Self-Regulation

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

GRATH: Gradual Self-Truthifying for Large Language Models

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

SHINE: Shielding Backdoors in Deep Reinforcement Learning

Agent Instructs Large Language Models to be General Zero-Shot Reasoners

Position: On the Societal Impact of Open Foundation Models

Robust Physical-World Attacks on Deep Learning Visual Classification

Fooling Vision and Language Models Despite Localization and Attention Mechanism

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

Natural Adversarial Examples

Model-Contrastive Federated Learning

Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification?

PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures

AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets

CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification

Improving Neural Program Synthesis with Inferred Execution Traces

Tree-to-tree Neural Networks for Program Translation

Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

Compositional Generalization via Neural-Symbolic Stack Machines

Towards practical differentially private causal graph discovery

Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis

Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams

Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages

How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios

Forecasting Future World Events With Neural Networks

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification