33 matches found
fides
Securing AI Agents with Information-Flow Control This repository contains a Jupyter notebook to accompany the academic paper "Securing AI Agents with Information-Flow Control". The notebook is structured as a tutorial to walk readers through the concepts introduced in the paper. This illustrates ...
Concealing LLM-Based Multi-Agent Topology Via Phantom Structure Injection
Driven by the rapid advancement of large language models LLMs, LLM-based multi-agent systems MAS have emerged as a powerful paradigm for collaborative reasoning over complex tasks. A key design element of MAS is the communication topology, which governs information flow among agents and often...
INTCC: A Framework for Interactive Confidential Computing
Confidential computing leverages Trusted Execution Environments TEEs to ensure the confidentiality and integrity of data in use. However, TEEs rely on remote attestation to guarantee the integrity of their initial memory state. This model is fundamentally at odds with interactive development...
Trusted Model Environment for Private Semantic Computations
A private semantic computation primitive enables parties to privately compute over structured and unstructured data that requires understanding its semantics, context, and relationships. Standard cryptographic primitives e.g., multiparty computation do not readily support such computation...
Automated Abstraction Refinement for Information Flow Security in Embedded Systems
Information flow analysis IFA is a powerful technique for verifying confidentiality and integrity and is therefore highly desirable for security-sensitive embedded systems. However, as these systems are inherently concurrent and time-dependent, existing IFA for embedded systems tend to be either...
Enhancing Privacy, Neglecting Harms: An Analysis of Real-World Digital Privacy Incidents
Privacy-enhancing technologies PETs have emerged as a technical means for providing individuals with greater control over their information. Yet despite the growing deployment of PETs, people continue to experience privacy harms. In this work, we revisit our understanding of privacy incidents and...
Efficient Hardware Information-Flow Tracking for Pre-Silicon Security Testing
Register-Transfer Level RTL simulation is widely used to test hardware before it is fabricated. To allow testing for security related information flow properties, such as confidentiality and integrity, taint logic can be automatically added to the design to track how information flows through it...
SPA: Securing Persistent LLM Agents across Queries with Plan-First Information-Flow Control
Large language model LLM agents increasingly operate over untrusted webpages, documents, tools, and persistent states while exercising authority over security-sensitive resources. Existing defenses typically protect either planning or individual tool interactions, but persistent agents face a...
SPARC: Automated Root-Cause Analysis of Pre-Silicon Power Side-Channel Leakage in the Processor Design Flow
Power-Side-Channel Leakage PSCL originates from architectural and micro-architectural artifacts in a processor and poses a severe threat to the confidentiality of cryptographic software. Consequently, pre-silicon PSCL evaluation is indispensable for secure hardware design. Existing frameworks are...
Twin Agent: Context Residual Compression for Privilege Separated Agents
Large language model LLM agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and...
Mechanised Operational Semantics of Rowhammer
Rowhammer is a hardware vulnerability in dynamic random-access memory DRAM in which repeated accesses to aggressor rows can induce bit-flips in victim rows. This phenomenon violates a core assumption of conventional programming language semantics: reading or writing one memory location does not...
Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
LLM coding agents increasingly rely on third-party agent skills from public marketplaces, which execute with the agent's privileges and create a software supply-chain attack surface: a malicious skill can steal credentials, exfiltrate source code, or install backdoors. Existing defenses use stati...
Information Flow Security on Persistent Memory
Persistent memory is a recently proposed memory paradigm that delivers many system-wide benefits, including improved runtime efficiency and the ability of programs to recover from power outages and system crashes. While recent research has investigated techniques for proving functional correctnes...
Information Flow Paths from RTL Traces
Security validation is an important yet challenging part of the hardware design process, yet, by convention, validation engineers are tasked with defining the threat model, specifying the relevant security properties, detecting any violations of those properties, and assessing the consequences to...
AI Agents May Always Fall for Prompt Injections
Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm data-instruction separation both fails to detect attacks that operate through contextual manipulation and degrades contextually appropriate behavior. We...
Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents
Autonomous Large Language Model LLM agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorize...
[SECURITY] Fedora 44 Update: kf6-purpose-6.25.0-1.fc44
Purpose offers the possibility to create integrate services and actions on any application without having to implement them specifically. Purpose will offer them mechanisms to list the different alternatives to execute given the requested action type and will facilitate components so that all the...
Optimizing Agent Planning for Security and Autonomy
Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies, but currently appear costly: they reduce task completion...
SecIC3: Customizing IC3 for Hardware Security Verification
Recent years have seen significant advances in using formal verification to check hardware security properties. Of particular practical interest are checking confidentiality and integrity of secrets, by checking that there is no information flow between the secrets and observable outputs. A...
