Ashwinee Panda
12 papers · 2020–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (19) π§ Keyword Pioneer π£ Hot Topic Early Bird π Renaissance Researcher (7) π Interdisciplinary Bridge
π
Conference Polyglot
(6)
π
Academic Marathon
(5)
π
Cross-Pollinator
(10)
π
Grand Slam
π
Century Club
(11)
Conferences
ICLR (4)
ICML (3)
AAAI (1)
ACL (1)
AISTATS (1)
EMNLP (1)
NIPS (1)
Top co-authors
Research topics
Keywords
federated learning
(3)
model poisoning
(2)
stochastic gradient descent
(2)
prior learning
(1)
benchmark evaluation
(1)
adversarial robustness
(1)
domain adaptation
(1)
adversarial machine learning
(1)
in-context learning
(1)
information retrieval
(1)
distributed learning
(1)
model alignment
(1)
contextual retrieval
(1)
communication efficiency
(1)
privacy utility tradeoff
(1)
semantic similarity
(1)
backdoor attack
(1)
adversarial defense
(1)
gradient clipping
(1)
vision-language model
(1)
Papers
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
ACL 2026
Safety Alignment Should be Made More Than Just a Few Tokens Deep
ICLR 2025
Beyond the Haystack: Sensitivity to Context in Legal Reference Recall
EMNLP 2025
Privacy Auditing of Large Language Models
ICLR 2025
Teach LLMs to Phish: Stealing Private Information from Language Models
ICLR 2024
Privacy-Preserving In-Context Learning for Large Language Models
ICLR 2024
Visual Adversarial Examples Jailbreak Aligned Large Language Models
AAAI 2024
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
ICML 2024
Differentially Private Image Classification by Learning Priors from Random Processes
NIPS 2023
Neurotoxin: Durable Backdoors in Federated Learning
ICML 2022
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
AISTATS 2022
FetchSGD: Communication-Efficient Federated Learning with Sketching
ICML 2020