FedTDP: a Privacy-Preserving and Unified Framework for Trajectory Data Preparation Via Federated Learning

Trajectory data, which capture the movement patterns of people and vehicles over time and space, are crucial for applications like traffic optimization and urban planning. However, issues such as noise and incompleteness often compromise data quality, leading to inaccurate trajectory analyses and...

A Survey on Privacy Risks and Protection in Large Language Models

Although Large Language Models LLMs have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. Firs...

VDDP: Verifiable Distributed Differential Privacy under the Client-Server-Verifier Setup

Despite differential privacy DP often being considered the de facto standard for data privacy, its realization is vulnerable to unfaithful execution of its mechanisms by servers, especially in distributed settings. Specifically, servers may sample noise from incorrect distributions or generate...

How to Backdoor the Knowledge Distillation

Knowledge distillation has become a cornerstone in modern machine learning systems, celebrated for its ability to transfer knowledge from a large, complex teacher model to a more efficient student model. Traditionally, this process is regarded as secure, assuming the teacher model is clean. This...

Traceback of Poisoning Attacks to Retrieval-Augmented Generation

Large language models LLMs integrated with retrieval-augmented generation RAG systems improve accuracy by leveraging external knowledge sources. However, recent research has revealed RAG's susceptibility to poisoning attacks, where the attacker injects poisoned texts into the knowledge database,...

Towards Fuzzing Zero-Knowledge Proof Circuits (Short Paper)

Whitepaper called Towards Fuzzing Zero-Knowledge Proof Circuits Short Paper...

Federated One-Shot Learning with Data Privacy and Objective-Hiding

Privacy in federated learning is crucial, encompassing two key aspects: safeguarding the privacy of clients' data and maintaining the privacy of the federator's objective from the clients. While the first aspect has been extensively studied, the second has received much less attention. We present...

VApps: Verifiable Applications at Internet Scale

Blockchain technology promises a decentralized, trustless, and interoperable infrastructure. However, widespread adoption remains hindered by issues such as limited scalability, high transaction costs, and the complexity of maintaining coherent verification logic across different blockchain layer...

From Paper Trails to Trust on Tracks: Adding Public Transparency to Railways Via Zk-SNARKs

Railways provide a critical service and operate under strict regulatory frameworks for implementing changes or upgrades. Despite their impact on the public, these frameworks do not define means or mechanisms for transparency towards the public, leading to reduced trust and complex tracking...

Trusted Compute Units: a Framework for Chained Verifiable Computations

Blockchain and distributed ledger technologies DLTs facilitate decentralized computations across trust boundaries. However, ensuring complex computations with low gas fees and confidentiality remains challenging. Recent advances in Confidential Computing -- leveraging hardware-based Trusted...

Hybrid Privacy Policy-Code Consistency Check Using Knowledge Graphs and LLMs

The increasing concern in user privacy misuse has accelerated research into checking consistencies between smartphone apps' declared privacy policies and their actual behaviors. Recent advances in Large Language Models LLMs have introduced promising techniques for semantic comparison, but these...

NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation

Large Language Models LLM are typically trained on vast amounts of data from various sources. Even when designed modularly e.g., Mixture-of-Experts, LLMs can leak privacy on their sources. Conversely, training such models in isolation arguably prohibits generalization. To this end, we propose a...

PICO: Secure Transformers Via Robust Prompt Isolation and Cybersecurity Oversight

We propose a robust transformer architecture designed to prevent prompt injection attacks and ensure secure, reliable response generation. Our PICO Prompt Isolation and Cybersecurity Oversight framework structurally separates trusted system instructions from untrusted user inputs through dual...

Biting the CHERI Bullet: Blockers, Enablers and Security Implications of CHERI in Defence

There is growing interest in securing the hardware foundations software stacks build upon. However, before making any investment decision, software and hardware supply chain stakeholders require evidence from realistic, multiple long-term studies of adoption. We present results from a 12 month...

"Shifting Access Control Left" Using Asset and Goal Models

Access control needs have broad design implications, but access control specifications may be elicited before, during, or after these needs are captured. Because access control knowledge is distributed, we need to make knowledge asymmetries more transparent, and use expertise already available to...

The vulnerability of the SAP KMC WPC knowledge management business application, related to deficiencies in the authentication process, allows unauthorized users to gain unauthorized access to protected information.

The vulnerability of the SAP KMC WPC knowledge management business application is related to deficiencies in the authentication process. Exploiting this vulnerability could allow an attacker, operating remotely, to gain unauthorized access to protected information...

Anonymous Public Announcements

We formalise the notion of an anonymous public announcement in the tradition of public announcement logic. Such announcements can be seen as in-between a public announcement from "the outside" an announcement of $φ$ and a public announcement by one of the agents an announcement of $Kaφ$: we get...

REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-To-Image Diffusion Models

The rapid advancement of generative AI highlights the importance of text-to-image T2I security, particularly with the threat of backdoor poisoning. Timely disclosure and mitigation of security vulnerabilities in T2I models are crucial for ensuring the safe deployment of generative models. We...

Post Quantum Cryptography (PQC) Signatures without Trapdoors

Some of our current public key methods use a trap door to implement digital signature methods. This includes the RSA method, which uses Fermat's little theorem to support the creation and verification of a digital signature. The problem with a back-door is that the actual trap-door method could, ...

The Digital Cybersecurity Expert: How Far Have We Come?

The increasing deployment of large language models LLMs in the cybersecurity domain underscores the need for effective model selection and evaluation. However, traditional evaluation methods often overlook specific cybersecurity knowledge gaps that contribute to performance limitations. To addres...