Matt Fredrikson
~Matt_Fredrikson1
11
论文总数
5.5
年均投稿
平均评分
接收情况7/11
会议分布
ICLR
7
NeurIPS
3
COLM
1
发表论文 (11 篇)
20255 篇
4
LLM-based Multi-Agents System Attack via Continuous Optimization with Discrete Efficient Search
COLM 2025Poster
4
Transferable Adversarial Attack on Vision-enabled Large Language Models
ICLR 2025withdrawn
4
Safety Pretraining: Toward the Next Generation of Safe AI
NeurIPS 2025Poster
4
Aligned LLMs Are Not Aligned Browser Agents
ICLR 2025Poster
4
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
ICLR 2025Poster
20246 篇
3
Centroid-Based Learning for Malware Detection and Novel Family Identification
ICLR 2024Rejected
3
A Recipe for Improved Certifiable Robustness
ICLR 2024Poster
5
Improving Alignment and Robustness with Circuit Breakers
NeurIPS 2024Poster
4
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
NeurIPS 2024Poster
4
Robustness Evaluation of Proxy Models against Adversarial Optimization
ICLR 2024Rejected
3
Enhancing Neural Network Transparency through Representation Analysis
ICLR 2024Rejected