Somesh Jha
~Somesh_Jha1
10
论文总数
5.0
年均投稿
平均评分
接收情况7/10
会议分布
ICLR
8
ICML
1
NeurIPS
1
发表论文 (10 篇)
20257 篇
4
AutoHijacker: Automatic Indirect Prompt Injection Against Black-box LLM Agents
ICLR 2025Rejected
5
Can Watermarks be Used to Detect LLM IP Infringement For Free?
ICLR 2025Poster
4
CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
ICLR 2025Poster
4
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
ICLR 2025Poster
4
Validating Mechanistic Interpretations: An Axiomatic Approach
ICML 2025Poster
4
What Really is a Member? Discrediting Membership Inference via Poisoning
NeurIPS 2025Poster
6
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
ICLR 2025Spotlight
20243 篇
4
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction
ICLR 2024withdrawn
4
Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection
ICLR 2024Rejected
4
On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
ICLR 2024Poster