Ashish Hooda

26 papers A* 6A 1Journal 18Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Auto-SPT: Automating Semantic Preserving Transformations for Code.
CoRR
Ashish Hooda, Mihai Christodorescu, Chuangang Ren, Aaron Wilson, Kassem Fawaz, Somesh Jha
2025 J jnl
Computing Optimization-Based Prompt Injections Against Closed-Weights Models By Misusing a Fine-Tuning API.
CoRR
Andrey Labunets, Nishit V. Pandya, Ashish Hooda, Xiaohan Fu, Earlence Fernandes
2025 A* conf
Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-Based Prompt Injection Attacks via the Fine-Tuning Interface.
SP
Andrey Labunets, Nishit V. Pandya, Ashish Hooda, Xiaohan Fu, Earlence Fernandes
2025 A* conf
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks.
ICLR
Zi Wang, Divyam Anshumaan, Ashish Hooda, Yudong Chen, Somesh Jha
2025 J jnl
Systems Security Foundations for Agentic Computing.
CoRR
Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha, Johann Rehberger, Khawaja Shams
2025 J jnl
Systems Security Foundations for Agentic Computing.
IACR Cryptol. ePrint Arch.
Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha, Johann Rehberger, Khawaja Shams
2025 J jnl
Through the Stealth Lens: Rethinking Attacks and Defenses in RAG.
CoRR
Sarthak Choudhary, Nils Palumbo, Ashish Hooda, Krishnamurthy Dj Dvijotham, Somesh Jha
2025 J jnl
What Really is a Member? Discrediting Membership Inference via Poisoning.
CoRR
Neal Mangaokar, Ashish Hooda, Zhuohang Li, Bradley A. Malin, Kassem Fawaz, Somesh Jha, Atul Prakash, Amrita Roy Chowdhury
2024 A conf
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles.
WACV
Ashish Hooda, Neal Mangaokar, Ryan Feng, Kassem Fawaz, Somesh Jha, Atul Prakash
2024 J jnl
Do Large Code Models Understand Programming Concepts? A Black-box Approach.
CoRR
Ashish Hooda, Mihai Christodorescu, Miltiadis Allamanis, Aaron Wilson, Kassem Fawaz, Somesh Jha
2024 A* conf
Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates.
ICML
Ashish Hooda, Mihai Christodorescu, Miltiadis Allamanis, Aaron Wilson, Kassem Fawaz, Somesh Jha
2024 A* conf
Experimental Analyses of the Physical Surveillance Risks in Client-Side Content Scanning.
NDSS
Ashish Hooda, Andrey Labunets, Tadayoshi Kohno, Earlence Fernandes
2024 J jnl
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks.
CoRR
Zi Wang, Divyam Anshumaan, Ashish Hooda, Yudong Chen, Somesh Jha
2024 — conf
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails.
ACL (1)
Neal Mangaokar, Ashish Hooda, Jihye Choi, Shreyas Chandrashekaran, Kassem Fawaz, Somesh Jha, Atul Prakash
2024 J jnl
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails.
CoRR
Neal Mangaokar, Ashish Hooda, Jihye Choi, Shreyas Chandrashekaran, Kassem Fawaz, Somesh Jha, Atul Prakash
2024 J jnl
PolicyLR: A Logic Representation For Privacy Policies.
CoRR
Ashish Hooda, Rishabh Khandelwal, Prasad Chalasani, Kassem Fawaz, Somesh Jha
2024 J jnl
Synthetic Counterfactual Faces.
CoRR
Guruprasad V. Ramesh, Harrison Rosenberg, Ashish Hooda, Shimaa Ahmed, Kassem Fawaz
2023 J jnl
Investigating Stateful Defenses Against Black-Box Adversarial Examples.
CoRR
Ryan Feng, Ashish Hooda, Neal Mangaokar, Kassem Fawaz, Somesh Jha, Atul Prakash
2023 A* conf
Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks.
CCS
Ryan Feng, Ashish Hooda, Neal Mangaokar, Kassem Fawaz, Somesh Jha, Atul Prakash
2023 J jnl
Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks.
CoRR
Ashish Hooda, Neal Mangaokar, Ryan Feng, Kassem Fawaz, Somesh Jha, Atul Prakash
2022 J jnl
Re-purposing Perceptual Hashing based Client Side Scanning for Physical Surveillance.
CoRR
Ashish Hooda, Andrey Labunets, Tadayoshi Kohno, Earlence Fernandes
2022 J jnl
SkillFence: A Systems Approach to Practically Mitigating Voice-Based Confusion Attacks.
CoRR
Ashish Hooda, Matthew Wallace, Kushal Jhunjhunwalla, Earlence Fernandes, Kassem Fawaz
2022 J jnl
SkillFence: A Systems Approach to Practically Mitigating Voice-Based Confusion Attacks.
Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.
Ashish Hooda, Matthew Wallace, Kushal Jhunjhunwalla, Earlence Fernandes, Kassem Fawaz
2022 J jnl
Towards Adversarially Robust Deepfake Detection: An Ensemble Approach.
CoRR
Ashish Hooda, Neal Mangaokar, Ryan Feng, Kassem Fawaz, Somesh Jha, Atul Prakash
2021 A* conf
Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effect.
CVPR
Athena Sayles, Ashish Hooda, Mohit Gupta, Rahul Chatterjee, Earlence Fernandes
2020 J jnl
Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effect.
CoRR
Athena Sayles, Ashish Hooda, Mohit Gupta, Rahul Chatterjee, Earlence Fernandes