Search Results for author:
Found 20 papers, 4 papers with code
Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas
The success of Large Language Models (LLMs) in multicultural environments hinges on their ability to understand users' diverse cultural backgrounds.
Understanding the limitations of self-supervised learning for tabular anomaly detection
While self-supervised learning has improved anomaly detection in computer vision and natural language processing, it is unclear whether tabular data can benefit from it.
Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities
Spurred by the recent rapid increase in the development and distribution of large language models (LLMs) across industry and academia, much recent work has drawn attention to safety- and security-related threats and vulnerabilities of LLMs, including in the context of potentially criminal activities.
Identifying Human Strategies for Generating Word-Level Adversarial Examples
Adversarial examples in NLP are receiving increasing research attention.
Using Forwards-Backwards Models to Approximate MDP Homomorphisms
Reinforcement learning agents must painstakingly learn through trial and error what sets of state-action pairs are value equivalent -- requiring an often prohibitively large amount of environment experience.
Self-Supervised Losses for One-Class Textual Anomaly Detection
The separability of anomalies and inliers signals that a representation is more effective for detecting semantic anomalies, whilst the presence of narrow feature directions signals a representation that is effective for detecting syntactic anomalies.
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs against certain criteria (e. g., the preservation of semantics and grammaticality).
Brittle Features May Help Anomaly Detection
In addition, separability between anomalies and normal data is important but not the sole factor for a good representation, as anomaly detection performance is also correlated with more adversarially brittle features in the representation space.
How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation
Exploration in environments with sparse rewards is difficult for artificial agents.
Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples
Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood.
Conditional Adversarial Camera Model Anonymization
Model anonymization is the process of transforming these artifacts such that the apparent capture model is changed.
Multiple-Identity Image Attacks Against Face-based Identity Verification
New quantitative results are presented that support an explanation in terms of the geometry of the representations spaces used by the verification systems.
‘Unexpected item in the bagging area’: Anomaly Detection in X-ray Security Images
The algorithms are tested on X-ray parcel images using stream-of-commerce data as the normal class, and parcels with firearms present as examples of anomalies to be detected.
A New Angle on L2 Regularization
Imagine two high-dimensional clusters and a hyperplane separating them.
Built-in Vulnerabilities to Imperceptible Adversarial Perturbations
Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult.
Automated detection of smuggled high-risk security threats using Deep Learning
In this contribution, we demonstrate for the first time the use of Convolutional Neural Networks (CNNs), a type of Deep Learning, to automate the detection of SMTs in fullsize X-ray images of cargo containers.
Automated X-ray Image Analysis for Cargo Security: Critical Review and Future Promise
We review the relatively immature field of automated image analysis for X-ray cargo imagery.
Detection of concealed cars in complex cargo X-ray imagery using Deep Learning
In this contribution, we describe a method for the detection of cars in X-ray cargo images based on trained-from-scratch Convolutional Neural Networks.
Better Image Segmentation by Exploiting Dense Semantic Predictions
The paper focuses on utilizing the FCNN-based dense semantic predictions in the bottom-up image segmentation, arguing to take semantic cues into account from the very beginning.
Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions
These units suppress signals of exceptional magnitude.
