Related papers: HBEE: Human Behavioral Entropy Engine -- Pre-Regis…

AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. We thus…

With the development of deep learning, Neural Code Models (NCMs) such as CodeBERT and CodeLlama are widely used for code understanding tasks, including defect detection and code classification. However, recent studies have revealed that…

Deep neural networks (DNNs) are inherently vulnerable to adversarial inputs: such maliciously crafted samples trigger DNNs to misbehave, leading to detrimental consequences for DNN-powered systems. The fundamental challenges of mitigating…

We investigate empathy-in-action -- the willingness to sacrifice task efficiency to address human needs -- as a linear direction in LLM activation space. Using contrastive prompts grounded in the Empathy-in-Action (EIA) benchmark, we test…

Machine learning models are vulnerable to adversarial inputs that induce seemingly unjustifiable errors. As automated classifiers are increasingly used in industrial control systems and machinery, these adversarial errors could grow to be a…

As Deep Neural Network (DNN) inference becomes increasingly prevalent on edge and mobile platforms, critical challenges emerge in privacy protection, resource constraints, and dynamic model deployment. This paper proposes a privacy-aware…

LLM evaluations drive which models get deployed, what safety standards get adopted, which research conclusions get published, and how projections of AI's labor-market impact get made. Yet standard confidence intervals ignore variability…

The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs…

Machine learning (ML)-based network intrusion detection is susceptible to attacks that perturb malicious network flows to evade detection. Existing approaches to evaluating the robustness of these models rely on gradient-based optimization…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to infer whether an input sample was used to train the model. Over the past few years,…

We study membership inference in settings where some of the assumptions typically used in previous research are relaxed. First, we consider skewed priors, to cover cases such as when only a small fraction of the candidate pool targeted by…

Emerging AR-LLM-based Social Engineering attack (e.g., SEAR) is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attack, the attacker can leverage AR (Augmented Reality) glass to capture the image and vocal…

We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight) lower bound on a policy's performance. This is crucial when…

Malware detection have used machine learning to detect malware in programs. These applications take in raw or processed binary data to neural network models to classify as benign or malicious files. Even though this approach has proven…

Increasing use of machine learning (ML) technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing…

Consider the task of estimating a 3-order $n \times n \times n$ tensor from noisy observations of randomly chosen entries in the sparse regime. We introduce a similarity based collaborative filtering algorithm for estimating a tensor from…

Large language models (LLMs) tend to follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. How deceptive instructions alter the internal representations of LLM compared to truthful ones remains…

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Recognizing complex behavioral states such as Ambivalence and Hesitancy (A/H) in naturalistic video settings remains a significant challenge in affective computing. Unlike basic facial expressions, A/H manifests as subtle, multimodal…

Over the years, the technological landscape has evolved, reshaping the security posture of organisations and increasing their exposure to cybersecurity threats, many originating from within. Insider threats remain a major challenge,…