Matt Fredrikson
22 papers · 2018–2026 · 7 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (30) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Keyword Champion
(2)
π
Triple Crown
π
Trend Setter
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(111)
Top co-authors
Research topics
Artificial Intelligence
(18)
Core AI Β· Artificial Intelligence
(18)
Machine Learning
(15)
Deep Learning
(11)
Optimization & Theory
(9)
Application Areas
(6)
Learning Types Β· Deep Learning
(4)
Learning Types Β· Machine Learning
(4)
Techniques
(4)
Architectures
(3)
Core Methods
(2)
Computer Vision
(1)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Core AI Β· Computer Vision
(1)
Keywords
adversarial robustness
(7)
adversarial attack
(5)
certified robustness
(3)
jailbreak attack
(3)
neural network
(3)
feature attribution
(2)
adversarial example
(2)
large language model
(2)
agent safety
(2)
decision boundary
(2)
certifiable robustness
(2)
feature selection
(1)
neural network interpretability
(1)
ai safety
(1)
adversarial training
(1)
algorithmic fairness
(1)
adversarial learning
(1)
data augmentation
(1)
hypothesis testing
(1)
model robustness
(1)
Papers
Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
ACL 2026
Omni-Attack: Adversarial Attacks on Open-Ended VQA in Black-Box Multimodal LLMs
CVPR 2026
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
ICLR 2025
Aligned LLMs Are Not Aligned Browser Agents
ICLR 2025
A Recipe for Improved Certifiable Robustness
ICLR 2024
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
NeurIPS 2024
Improving Alignment and Robustness with Circuit Breakers
NeurIPS 2024
Grounding Neural Inference with Satisfiability Modulo Theories
NeurIPS 2023
On the Perils of Cascading Robust Classifiers
ICLR 2023
Unlocking Deterministic Robustness Certification on ImageNet
NeurIPS 2023
Consistent Counterfactuals for Deep Models
ICLR 2022
Robust Models Are More Interpretable Because Attributions Look Normal
ICML 2022
Selective Ensembles for Consistent Predictions
ICLR 2022
Fast Geometric Projections for Local Robustness Certification
ICLR 2021
Globally-Robust Neural Networks
ICML 2021
Relaxing Local Robustness
NeurIPS 2021
Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness
IJCAI 2020
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models
ACL 2020
Learning Fair Representations for Kernel Models
AISTATS 2020
Smoothed Geometry for Robust Attribution
NeurIPS 2020
Feature-Wise Bias Amplification
ICLR 2019
Hunting for Discriminatory Proxies in Linear Regression Models
NeurIPS 2018