3 citations · 4 across the 10 of their papers we have counts for
12 papers
LLMs Learn to Evade Latent Monitors from Prior Feedback Alone
Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani
Latent space monitors aim to detect undesired behaviors in LLM agents by inspecting an agent's internal activations rather than its outputs. However, interactive monitoring creates…
VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1
Object hallucination remains a persistent reliability issue in large vision-language models, where generated object mentions may sound plausible but lack visual grounding. Recent t…
GeoDetect: Geometric Adversarial Detection for VLPs
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +2
Vision-language pre-trained models (VLPs) are widely used in real-world applications. However, they remain vulnerable to adversarial attacks. Although adversarial detection methods…
Semantic Robustness Certification for Vision-Language Models
Peiyu Yang, Paul Montague, Feng Liu +4
Vision-language models (VLMs) are now widely used in downstream tasks. However, real-world applications often expose VLMs to distribution shifts induced by semantic variation (e.g.…
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1
Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification. However, their predictions remain sensitive to spurious correlations, where contextual cues…
TRACER: Persistent Regularization for Robust Multimodal Finetuning
Hesam Asadollahzadeh, Feng Liu, Christopher Leckie +1
Mainstream strategies for finetuning pretrained multimodal models often degrade out-of-distribution (OOD) robustness, a phenomenon known as catastrophic forgetting. In this paper,…
Mechanistic Anomaly Detection via Functional Attribution
Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani
We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was produced by normal or anomalous int…
Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection
Nimeshika Udayangani, Hadi M. Dolatabadi, Sarah Erfani +1
Detecting out-of-distribution (OOD) data is essential for safe deployment of deep neural networks (DNNs). This problem becomes particularly challenging in the presence of long-tail…
Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimension
Canaan Yung, Hanxun Huang, Christopher Leckie +1
Adversarial prompts are capable of jailbreaking frontier large language models (LLMs) and inducing undesirable behaviours, posing a significant obstacle to their safe deployment. C…
HALO: Robust Out-of-Distribution Detection via Joint Optimisation
Hugo Lyons Keenan, Sarah Erfani, Christopher Leckie
Effective out-of-distribution (OOD) detection is crucial for the safe deployment of machine learning models in real-world scenarios. However, recent work has shown that OOD detecti…
Round Trip Translation Defence against Large Language Model Jailbreaking Attacks
Canaan Yung, Hadi Mohaghegh Dolatabadi, Sarah Erfani +1
Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing de…
Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning
Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie
Deep neural networks (DNNs) are vulnerable to shortcut learning: rather than learning the intended task, they tend to draw inconclusive relationships between their inputs and outpu…