2 citations · 7 across the 16 of their papers we have counts for
8 papers · 1 filter
From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents
Juanyang Xu, Zheng Wang, Xingyu Zhao +2
When the harmfulness of an LLM agent's output can be quantified, a natural jailbreaking objective is to maximize expected harmfulness over admissible input modifications. An altern…
Probabilistic Adversarial Training
Andi Zhang, Xingyu Zhao, Siddartha Khastgir
Building on a probabilistic perspective in which adversarial examples arise from the overlap between a distance-based distribution and a victim-classifier-induce…
Let the Carrier Carry the Attack: Preserving the Subject in Adversarial Image Generation
Linfeng Jiang, Steven McDonagh, Yuhang Chen +3
Strong unrestricted adversarial attacks can distort the primary object of an image, hereafter referred to as the subject. To preserve subject integrity without compromising attack…
Reusing Operational Evidence After Context Changes: A Conservative Bayesian Framework for Autonomous Vehicle Safety
Robab Aghazadeh Chakherlou, Siddartha Khastgir, Xingyu Zhao
Operational evidence, i.e., evidence of operation without failure is an important component of confidence in the safety or reliability of a system in service, but it is costly to c…
Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model
Robab Aghazadeh Chakherlou, Siddartha Khastgir, Peter Popov +1
Reliability assessment of large language models (LLMs) seeks to estimate the probability that a model produces correct responses under a specified operational profile. Conventional…
Probabilistic Robustness in Medical Image Classification
Yi Zhang, Siddartha Khastgir, Xingyu Zhao
Deep learning (DL) has shown strong performance in medical image classification, but its trustworthy deployment remains challenging in safety-critical clinical settings, where pred…
Quantifying Fidelity: A Decisive Feature Approach to Comparing Synthetic and Real Imagery
Danial Safaei, Siddartha Khastgir, Mohsen Alirezaei +4
Virtual testing using synthetic data has become a cornerstone of autonomous vehicle (AV) safety assurance. Despite progress in improving visual realism through advanced simulators…
Introducing a Novel Systems Thinking approach inspired by STPA: Road Safety Intervention design case study
Halima El Badaoui, Siddartha Khastgir, Mariat James Elizebeth +3
According to the latest provisional statistics released by the UK Department for Transport, Great Britain recorded 1,633 road deaths in 2024, representing a slight increase from 20…