Prateek Mittal
~Prateek_Mittal1
16
论文总数
8.0
年均投稿
平均评分
接收情况14/16
会议分布
ICLR
13
NeurIPS
2
ICML
1
发表论文 (16 篇)
202511 篇
4
Data Shapley in One Training Run
ICLR 2025Oral
4
Adapting to Evolving Adversaries with Regularized Continual Robust Training
ICML 2025Poster
4
Capturing the Temporal Dependence of Training Data Influence
ICLR 2025Oral
4
Privacy Auditing of Large Language Models
ICLR 2025Poster
4
ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
NeurIPS 2025Poster
4
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
ICLR 2025withdrawn
3
Certifiably Robust RAG against Retrieval Corruption Attacks
ICLR 2025Rejected
4
Safety Alignment Should be Made More Than Just a Few Tokens Deep
ICLR 2025Oral
4
On Evaluating the Durability of Safeguards for Open-Weight LLMs
ICLR 2025Poster
4
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
ICLR 2025Poster
4
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
ICLR 2025Poster
20245 篇
5
GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration
NeurIPS 2024Spotlight
4
Privacy-Preserving In-Context Learning for Large Language Models
ICLR 2024Poster
3
Teach LLMs to Phish: Stealing Private Information from Language Models
ICLR 2024Poster
4
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
ICLR 2024Oral
4
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
ICLR 2024Poster