PPaperPicks

Prateek Mittal

23 papers at tracked venues · 22 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ICLR ×12ICML ×3AAAI ×2NeurIPS ×2ACL ×1AISTATS ×1CHI ×1CVPR ×1

Frequent coauthors

Jiachen T. Wang
DBLP profile ↗ORCID search ↗
×4
Xiangyu Qi
DBLP profile ↗ORCID search ↗
×4
Tinghao Xie
DBLP profile ↗ORCID search ↗
×3
Ashwinee Panda
DBLP profile ↗ORCID search ↗
×3
Tong Wu
DBLP profile ↗ORCID search ↗
×2
Pengyuan Wei
DBLP profile ↗ORCID search ↗
×1
Sihui Dai
DBLP profile ↗ORCID search ↗
×1
Dennis Jacob
DBLP profile ↗ORCID search ↗
×1
Zeyu Shen
DBLP profile ↗ORCID search ↗
×1
Boyi Wei
DBLP profile ↗ORCID search ↗
×1
Josue Ortega Caro
DBLP profile ↗ORCID search ↗
×1
Lei Gao
DBLP profile ↗ORCID search ↗
×1

Papers

  1. AcoustoReinforce: Multi-Particle Acoustophoretic Path Planning with Deep Reinforcement Learning
    AAAI 2026 ·
    Pengyuan Wei
    DBLP profile ↗ORCID search ↗
  2. Red-Teaming NSFW Image Classifiers as Text-to-Image Safeguards
    ACL 2026 ·
    Tinghao Xie
    DBLP profile ↗ORCID search ↗
  3. Adapting to Evolving Adversaries with Regularized Continual Robust Training
    ICML 2025 ·
    Sihui Dai
    DBLP profile ↗ORCID search ↗
  4. Capturing the Temporal Dependence of Training Data Influence
    ICLR 2025 ·
    Jiachen T. Wang
    DBLP profile ↗ORCID search ↗
  5. Data Shapley in One Training Run
    ICLR 2025 ·
    Jiachen T. Wang
    DBLP profile ↗ORCID search ↗
  6. Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
    ICLR 2025 ·
    Tong Wu
    DBLP profile ↗ORCID search ↗
  7. On Evaluating the Durability of Safeguards for Open-Weight LLMs
    ICLR 2025 ·
    Xiangyu Qi
    DBLP profile ↗ORCID search ↗
  8. PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
    CVPR 2025 ·
    Dennis Jacob
    DBLP profile ↗ORCID search ↗
  9. Privacy Auditing of Large Language Models
    ICLR 2025 ·
    Ashwinee Panda
    DBLP profile ↗ORCID search ↗
  10. ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
    NeurIPS 2025 ·
    Zeyu Shen
    DBLP profile ↗ORCID search ↗
  11. SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
    ICLR 2025 ·
    Tinghao Xie
    DBLP profile ↗ORCID search ↗
  12. Safety Alignment Should be Made More Than Just a Few Tokens Deep
    ICLR 2025 ·
    Xiangyu Qi
    DBLP profile ↗ORCID search ↗
  13. A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
    ICML 2024 ·
    Ashwinee Panda
    DBLP profile ↗ORCID search ↗
  14. Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
    ICML 2024 ·
    Boyi Wei
    DBLP profile ↗ORCID search ↗
  15. BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
    ICLR 2024 ·
    Tinghao Xie
    DBLP profile ↗ORCID search ↗
  16. BrainLM: A foundation model for brain activity recordings
    ICLR 2024 ·
    Josue Ortega Caro
    DBLP profile ↗ORCID search ↗
  17. Efficient Data Shapley for Weighted Nearest Neighbor Algorithms
    AISTATS 2024 ·
    Jiachen T. Wang
    DBLP profile ↗ORCID search ↗
  18. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
    ICLR 2024 ·
    Xiangyu Qi
    DBLP profile ↗ORCID search ↗
  19. GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration
    NeurIPS 2024 ·
    Jiachen T. Wang
    DBLP profile ↗ORCID search ↗
  20. Privacy-Preserving In-Context Learning for Large Language Models
    ICLR 2024 ·
    Tong Wu
    DBLP profile ↗ORCID search ↗
  21. StableLev: Data-Driven Stability Enhancement for Multi-Particle Acoustic Levitation
    CHI 2024 ·
    Lei Gao
    DBLP profile ↗ORCID search ↗
  22. Teach LLMs to Phish: Stealing Private Information from Language Models
    ICLR 2024 ·
    Ashwinee Panda
    DBLP profile ↗ORCID search ↗
  23. Visual Adversarial Examples Jailbreak Aligned Large Language Models
    AAAI 2024 ·
    Xiangyu Qi
    DBLP profile ↗ORCID search ↗