Related papers: A New Enforcement on Declassification with Reachab…

When users make personal privacy choices, correlation between their data can cause inadvertent leakage about users who do not want to share their data by other users sharing their data. As a solution, we consider local redaction mechanisms.…

We study differentially private data release, where a database is accessed through successive, possibly adaptive queries and mechanisms. Existing composition theorems and privacy filters combine worst case per-round privacy parameters,…

Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information…

Side-channel attacks that leak sensitive information through a computing device's interaction with its physical environment have proven to be a severe threat to devices' security, particularly when adversaries have unfettered physical…

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…

Large Language Models (LLMs) can be misused to spread unwanted content at scale. Content watermarking deters misuse by hiding messages in content, enabling its detection using a secret watermarking key. Robustness is a core security…

Constant-time programming is a countermeasure to prevent cache based attacks where programs should not perform memory accesses that depend on secrets. In some cases this policy can be safely relaxed if one can prove that the program does…

Privacy attacks on machine learning models aim to identify the data that is used to train such models. Such attacks, traditionally, are studied on static models that are trained once and are accessible by the adversary. Motivated to meet…

A recent watermarking scheme for language models achieves distortion-free embedding and robustness to edit-distance attacks. However, it suffers from limited generation diversity and high detection overhead. In parallel, recent research has…

Language Models (LMs) may acquire harmful knowledge, and yet feign ignorance of these topics when under audit. Inspired by the recent discovery of deception-related behaviour patterns in LMs, we aim to train classifiers that detect when a…

We study an information-theoretic privacy mechanism design, where an agent observes useful data $Y$ and wants to reveal the information to a user. Since the useful data is correlated with the private data $X$, the agent uses a privacy…

Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…

Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…

This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution. Specifically, building on the work of Huang et al. (2021), we extend their bi-level…

Metric Differential Privacy is a generalization of differential privacy tailored to address the unique challenges of text-to-text privatization. By adding noise to the representation of words in the geometric space of embeddings, words are…

Technology advances in areas such as sensors, IoT, and robotics, enable new collaborative applications (e.g., autonomous devices). A primary requirement for such collaborations is to have a secure system which enables information sharing…

Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…

As an information-flow privacy property, opacity characterizes whether a malicious external observer (referred to as an intruder) is able to infer the secret behavior of a system. This paper addresses the problem of opacity enforcement…

As Large Language Models (LLMs) are increasingly deployed in sensitive domains, traditional data privacy measures prove inadequate for protecting information that is implicit, contextual, or inferable - what we define as semantic privacy.…