Siddharth Garg — accepted AI-conference papers

2026

Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning

Sara Ghazanfari, Francesco Croce, Nicolas Flammarion, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg

CVPR 2026

Recent work has shown that eliciting Large Language Models (LLMs) to generate reasoning traces in natural language before answering the user's request can significantly improve their performance across tasks. This approach has been extended to multimodal LLMs, where the models can produce chains-of-

Cited by 0 Source ↗code ↗Scholar ↗

2026

MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs

Boyuan Chen, Minghao Shao, Abdul Basit, Siddharth Garg, Muhammad Shafique

AAAI 2026technical

Large language models (LLMs) face persistent vulnerability to jailbreak attacks despite their increasing capabilities. While developers deploy alignment finetuning and safety guardrails, researchers consistently devise novel attacks that circumvent these defenses. This dynamic mirrors a strategic ga

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code

Raghu Vamshi Hemadri, Jitendra Bhandari, Andre Nakkab, Johann Knechtel, Badri P Gopalan, Ramesh Narayanaswamy +2

NeurIPS 2025poster

Modern chip design is complex, and there is a crucial need for early-stage prediction of key design-quality metrics like timing and routing congestion directly from Verilog code (a commonly used programming language for hardware design). It is especially important yet complex to predict individual…

Cited by 0 Source ↗Scholar ↗

2025

VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification

Patrick Yubeaton, Andre Nakkab, Weihua Xiao, Luca Collini, Ramesh Karri, Chinmay Hegde +1

NeurIPS 2025poster

This paper introduces VeriThoughts, a novel dataset designed for reasoning-based Verilog code generation. We establish a new benchmark framework grounded in formal verification methods to evaluate the quality and correctness of generated hardware descriptions. Additionally, we present a suite of spe…

Cited by 0 Source ↗code ↗Scholar ↗

2024

LipSim: A Provably Robust Perceptual Similarity Metric

Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg

ICLR 2024poster

Recent years have seen growing interest in developing and applying perceptual similarity metrics. Research has shown the superiority of perceptual metrics over pixel-wise metrics in aligning with human perception and serving as a proxy for the human visual system. On the other hand, as perceptual me…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2024

NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security

Minghao Shao, Sofija Jancheska, Meet Udeshi, Brendan Dolan-Gavitt, Haoran Xi, Kimberly Milner +7

NeurIPS 2024poster

Large Language Models (LLMs) are being deployed across various domains today. However, their capacity to solve Capture the Flag (CTF) challenges in cybersecurity has not been thoroughly evaluated. To address this, we develop a novel method to assess LLMs in solving CTF challenges by creating a scala…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2024

Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations

Patricia Pauli, Aaron J Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer +1

ICLR 2024poster

Recently, semidefinite programming (SDP) techniques have shown great promise in providing accurate Lipschitz bounds for neural networks. Specifically, the LipSDP approach (Fazlyab et al., 2019) has received much attention and provides the least conservative Lipschitz upper bounds that can be compute…

Cited by 6 Source ↗PDF ↗Scholar ↗

2024

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem

Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad khorrami, Siddharth Garg

AISTATS 2024poster

We introduce a formal statistical definition for the problem of backdoor detection in machine learning systems and use it to analyze the feasibility of such problems, providing evidence for the utility and applicability of our definition. The main contributions of this work are an impossibility resu…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2024

Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization

Animesh Basak Chowdhury, Marco Romanelli, Benjamin Tan, Ramesh Karri, Siddharth Garg

ICLR 2024poster

Logic synthesis, a pivotal stage in chip design, entails optimizing chip specifications encoded in hardware description languages like Verilog into highly efficient implementations using Boolean logic gates. The process involves a sequential application of logic minimization heuristics (``synthesis…

Cited by 5 Source ↗PDF ↗Scholar ↗

2023

Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models

Aaron J Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Bin Hu

NeurIPS 2023poster

Recently, deep equilibrium models (DEQs) have drawn increasing attention from the machine learning community. However, DEQs are much less understood in terms of certified robustness than their explicit network counterparts. In this paper, we advance the understanding of certified robustness of DEQs…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗

2023

Path Planning Under Uncertainty to Localize mmWave Sources

Kai Pfeiffer, Yuze Jia, Mingsheng Yin, Akshaj Kumar Veldanda, Yaqi Hu, Amee Trivedi +5

ICRA 2023poster

In this paper, we study a navigation problem where a mobile robot needs to locate a mmWave wireless signal. Using the directionality properties of the signal, we propose an estimation and path planning algorithm that can efficiently navigate in cluttered indoor environments. We formulate Extended Ka…

Cited by 6 Source ↗Scholar ↗

2023

Towards better certified segmentation via diffusion models

Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Marie-Pierre Revel, Siddharth Garg, Farshad Khorrami +1

UAI 2023poster

The robustness of image segmentation has been an important research topic in the past few years as segmentation models have reached production-level accuracy. However, like classification models, segmentation models can be vulnerable to adversarial perturbations, which hinders their use in critical-…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2022

Selective Network Linearization for Efficient Private Inference

Minsu Cho, Ameya Joshi, Brandon Reagen, Siddharth Garg, Chinmay Hegde

ICML 2022spotlight

Private inference (PI) enables inferences directly on cryptographically secure data. While promising to address many privacy issues, it has seen limited use due to extreme runtimes. Unlike plaintext inference, where latency is dominated by FLOPs, in PI non-linear functions (namely ReLU) are the bott…

Cited by 52 Source ↗PDF ↗code ↗Scholar ↗

2021

Circa: Stochastic ReLUs for Private Deep Learning

Zahra Ghodsi, Nandan Kumar Jha, Brandon Reagen, Siddharth Garg

NeurIPS 2021poster

The simultaneous rise of machine learning as a service and concerns over user privacy have increasingly motivated the need for private inference (PI). While recent work demonstrates PI is possible using cryptographic primitives, the computational overheads render it impractical. State-of-art deep ne…

Cited by 41 Source ↗PDF ↗Scholar ↗

2021

DeepReDuce: ReLU Reduction for Fast Private Inference

Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, Brandon Reagen

ICML 2021spotlight

The recent rise of privacy concerns has led researchers to devise methods for private neural inference—where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private inference is that computing on encrypted data levies an impractically-high latency pe…

Cited by 114 Source ↗PDF ↗Scholar ↗

2020

CryptoNAS: Private Inference on a ReLU Budget

Zahra Ghodsi, Akshaj Kumar Veldanda, Brandon Reagen, Siddharth Garg

NeurIPS 2020poster

Machine learning as a service has given raise to privacy concerns surrounding clients' data and providers' models and has catalyzed research in private inference (PI): methods to process inferences without disclosing inputs. Recently, researchers have adapted cryptographic techniques to show PI is p…

Cited by 106 Source ↗PDF ↗Scholar ↗

2019

Adaptive Adversarial Videos on Roadside Billboards: Dynamically Modifying Trajectories of Autonomous Vehicles

Naman Patel, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami

IROS 2019poster

Deep neural networks (DNNs) are being incorporated into various autonomous systems like self-driving cars and robots. However, there is a rising concern about the robustness of these systems because of their susceptibility to adversarial attacks on DNNs. Past research has established that DNNs used…

Cited by 21 Source ↗Scholar ↗

2017

SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud

Zahra Ghodsi, Tianyu Gu, Siddharth Garg

NeurIPS 2017poster

Inference using deep neural networks is often outsourced to the cloud since it is a computationally demanding task. However, this raises a fundamental issue of trust. How can a client be sure that the cloud has performed inference correctly? A lazy cloud provider might use a simpler but less accura…

Cited by 237 Source ↗PDF ↗Scholar ↗