default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAshwinee Panda
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[j3]Xinyu Tang
, Ashwinee Panda, Vikash Sehwag, Prateek Mittal:
Differentially Private Image Classification by Learning Priors from Random Processes. J. Priv. Confidentiality 15(1) (2025)- [j2]Xinyu Tang, Ashwinee Panda, Milad Nasr, Saeed Mahloujifar, Prateek Mittal:
Private Fine-tuning of Large Language Models with Zeroth-order Optimization. Trans. Mach. Learn. Res. 2025 (2025) - [j1]Benjamin Thérien, Charles-Étienne Joseph, Zain Sarwar, Ashwinee Panda, Anirban Das, Shi-Xiong Zhang, Stephen Rawls, Sambit Sahu, Eugene Belilovsky, Irina Rish:
Continual Pre-training of MoEs: How robust is your router? Trans. Mach. Learn. Res. 2025 (2025) - [c12]Ashwinee Panda, Xinyu Tang, Christopher A. Choquette-Choo, Milad Nasr, Prateek Mittal:
Privacy Auditing of Large Language Models. ICLR 2025 - [c11]Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson:
Safety Alignment Should be Made More Than Just a Few Tokens Deep. ICLR 2025 - [i30]Sean McLeish, John Kirchenbauer, David Yu Miller, Siddharth Singh, Abhinav Bhatele, Micah Goldblum, Ashwinee Panda, Tom Goldstein:
Gemstones: A Model Suite for Multi-Faceted Scaling Laws. CoRR abs/2502.06857 (2025) - [i29]Benjamin Thérien, Charles-Étienne Joseph, Zain Sarwar, Ashwinee Panda, Anirban Das, Shi-Xiong Zhang, Stephen Rawls, Sambit Sahu, Eugene Belilovsky, Irina Rish:
Continual Pre-training of MoEs: How robust is your router? CoRR abs/2503.05029 (2025) - [i28]Ashwinee Panda, Xinyu Tang, Milad Nasr, Christopher A. Choquette-Choo, Prateek Mittal:
Privacy Auditing of Large Language Models. CoRR abs/2503.06808 (2025) - [i27]Pedro Sandoval Segura, Xijun Wang, Ashwinee Panda, Micah Goldblum, Ronen Basri, Tom Goldstein, David Jacobs:
Using Attention Sinks to Identify and Evaluate Dormant Heads in Pretrained LLMs. CoRR abs/2504.03889 (2025) - [i26]Juzheng Zhang, Jiacheng You, Ashwinee Panda, Tom Goldstein:
LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation. CoRR abs/2504.07448 (2025) - [i25]Yuxin Wen, Jim Wu, Ajay Jain, Tom Goldstein, Ashwinee Panda:
Analysis of Attention in Video Diffusion Transformers. CoRR abs/2504.10317 (2025) - [i24]Ashwinee Panda, Vatsal Baherwani, Zain Sarwar, Benjamin Thérien, Supriyo Chakraborty, Tom Goldstein:
Dense Backpropagation Improves Training for Sparse Mixture-of-Experts. CoRR abs/2504.12463 (2025) - [i23]Monte Hoover, Vatsal Baherwani, Neel Jain, Khalid Saifullah, Joseph Vincent, Chirag Jain, Melissa Kazemi Rad, C. Bayan Bruss, Ashwinee Panda, Tom Goldstein:
DynaGuard: A Dynamic Guardrail Model With User-Defined Policies. CoRR abs/2509.02563 (2025) - [i22]Maheep Chaudhary, Ian Su, Nikhil Hooda, Nishith Shankar, Julia Tan, Kevin Zhu, Ashwinee Panda, Ryan Lagasse, Vasu Sharma:
Evaluation Awareness Scales Predictably in Open-Weights Large Language Models. CoRR abs/2509.13333 (2025) - [i21]Anand Swaroop, Akshat Nallani, Saksham Uboweja, Adiliia Uzdenova, Michael Nguyen, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary:
FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness. CoRR abs/2509.13334 (2025) - [i20]Nathan Egbuna, Saatvik Gaur, Sunishchal Dev, Ashwinee Panda, Maheep Chaudhary:
Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization. CoRR abs/2509.18116 (2025) - [i19]Nikita Afonin, Nikita Andriyanov, Nikhil Bageshpura, Kyle Liu, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Alexander Panchenko, Oleg Rogov, Elena Tutubalina, Mikhail Seleznyov:
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs. CoRR abs/2510.11288 (2025) - [i18]Daniel Aarao Reis Arturi, Eric Zhang, Andrew Ansah, Kevin Zhu, Ashwinee Panda, Aishwarya Balwani:
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior. CoRR abs/2511.02022 (2025) - [i17]Dev Patel, Gabrielle Gervacio, Diekola Raimi, Kevin Zhu, Ryan Lagasse, Gabriel Grand, Ashwinee Panda, Maheep Chaudhary:
Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits. CoRR abs/2511.07482 (2025) - [i16]Shourya Batra, Pierce Tillman, Samarth Gaggar, Shashank Kesineni, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary:
SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought. CoRR abs/2511.07772 (2025) - [i15]Jiahang He, Rishi Ramachandran, Neel Ramachandran, Aryan Katakam, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Aryan Shrivastava:
Modeling and Predicting Multi-Turn Answer Instability in Large Language Models. CoRR abs/2511.10688 (2025) - [i14]Kevin David Hayes, Micah Goldblum, Vikash Sehwag, Gowthami Somepalli, Ashwinee Panda, Tom Goldstein:
FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges. CoRR abs/2512.02161 (2025) - [i13]Isha Chaturvedi, Anjana Nair, Yushen Li, Adhitya Rajendra Kumar, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma:
Peek-a-Boo Reasoning: Contrastive Region Masking in MLLMs. CoRR abs/2512.08976 (2025) - 2024
- [c10]Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Peter Henderson, Mengdi Wang, Prateek Mittal:
Visual Adversarial Examples Jailbreak Aligned Large Language Models. AAAI 2024: 21527-21536 - [c9]Ashwinee Panda, Vatsal Baherwani, Zain Sarwar, Benjamin Thérien, Sambit Sahu, Stephen Rawls, Supriyo Chakraborty, Tom Goldstein:
Dense Backpropagation Improves Routing for Sparsely-Gated Mixture-of-Experts. ENLSP 2024: 81-101 - [c8]Zain Sarwar, Ashwinee Panda, Benjamin Thérien, Stephen Rawls, Anirban Das, Kartik Balasubramaniam, Berkcan Kapusuzoglu, Shixiong Zhang, Sambit Sahu, Milind Naphade, Supriyo Chakraborty:
StructMoE: Structured Mixture of Experts Using Low Rank Experts. ENLSP 2024: 182-193 - [c7]Ashwinee Panda, Christopher A. Choquette-Choo, Zhengming Zhang, Yaoqing Yang, Prateek Mittal:
Teach LLMs to Phish: Stealing Private Information from Language Models. ICLR 2024 - [c6]Tong Wu, Ashwinee Panda, Jiachen T. Wang, Prateek Mittal:
Privacy-Preserving In-Context Learning for Large Language Models. ICLR 2024 - [c5]Ashwinee Panda, Xinyu Tang, Saeed Mahloujifar, Vikash Sehwag, Prateek Mittal:
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization. ICML 2024 - [i12]Xinyu Tang, Ashwinee Panda, Milad Nasr, Saeed Mahloujifar, Prateek Mittal:
Private Fine-tuning of Large Language Models with Zeroth-order Optimization. CoRR abs/2401.04343 (2024) - [i11]Ashwinee Panda, Christopher A. Choquette-Choo, Zhengming Zhang, Yaoqing Yang, Prateek Mittal:
Teach LLMs to Phish: Stealing Private Information from Language Models. CoRR abs/2403.00871 (2024) - [i10]Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson:
Safety Alignment Should Be Made More Than Just a Few Tokens Deep. CoRR abs/2406.05946 (2024) - [i9]Ashwinee Panda, Berivan Isik, Xiangyu Qi, Sanmi Koyejo, Tsachy Weissman, Prateek Mittal:
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs. CoRR abs/2406.16797 (2024) - [i8]Neel Jain, Aditya Shrivastava, Chen Zhu, Daben Liu, Alfy Samuel, Ashwinee Panda, Anoop Kumar, Micah Goldblum, Tom Goldstein:
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models. CoRR abs/2412.06748 (2024) - 2023
- [c4]Xinyu Tang, Ashwinee Panda, Vikash Sehwag, Prateek Mittal:
Differentially Private Image Classification by Learning Priors from Random Processes. NeurIPS 2023 - [i7]Ashwinee Panda, Tong Wu, Jiachen T. Wang, Prateek Mittal:
Differentially Private In-Context Learning. CoRR abs/2305.01639 (2023) - [i6]Xinyu Tang, Ashwinee Panda, Vikash Sehwag, Prateek Mittal:
Differentially Private Image Classification by Learning Priors from Random Processes. CoRR abs/2306.06076 (2023) - [i5]Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Mengdi Wang, Prateek Mittal:
Visual Adversarial Examples Jailbreak Large Language Models. CoRR abs/2306.13213 (2023) - 2022
- [c3]Ashwinee Panda, Saeed Mahloujifar, Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal:
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification. AISTATS 2022: 7587-7624 - [c2]Zhengming Zhang, Ashwinee Panda, Linyue Song, Yaoqing Yang, Michael W. Mahoney, Prateek Mittal, Kannan Ramchandran, Joseph Gonzalez:
Neurotoxin: Durable Backdoors in Federated Learning. ICML 2022: 26429-26446 - [i4]Zhengming Zhang, Ashwinee Panda, Linyue Song, Yaoqing Yang, Michael W. Mahoney, Joseph E. Gonzalez, Kannan Ramchandran, Prateek Mittal:
Neurotoxin: Durable Backdoors in Federated Learning. CoRR abs/2206.10341 (2022) - [i3]Ashwinee Panda, Xinyu Tang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal:
DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning. CoRR abs/2212.04486 (2022) - 2021
- [i2]Ashwinee Panda, Saeed Mahloujifar, Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal:
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification. CoRR abs/2112.06274 (2021) - 2020
- [c1]Daniel Rothchild, Ashwinee Panda, Enayat Ullah, Nikita Ivkin, Ion Stoica, Vladimir Braverman, Joseph Gonzalez, Raman Arora:
FetchSGD: Communication-Efficient Federated Learning with Sketching. ICML 2020: 8253-8265 - [i1]Daniel Rothchild, Ashwinee Panda, Enayat Ullah, Nikita Ivkin, Ion Stoica, Vladimir Braverman, Joseph Gonzalez, Raman Arora:
FetchSGD: Communication-Efficient Federated Learning with Sketching. CoRR abs/2007.07682 (2020)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2026-01-24 23:43 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
