Related papers: Enforcing Benign Trajectories: A Behavioral Firewa…
Detecting stealthy malicious communications from flow logs under benign-only training remains a critical challenge in network security. Malicious communications often camouflage as normal traffic like standard HTTPS flows. Conventional…
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…
Web applications increasingly face evasive and polymorphic attack payloads, yet traditional web application firewalls (WAFs) based on static rule sets such as the OWASP Core Rule Set (CRS) often miss obfuscated or zero-day patterns without…
The recent advance in autonomous underwater robotics facilitates autonomous inspection tasks of offshore infrastructure. However, current inspection missions rely on predefined plans created offline, hampering the flexibility and autonomy…
Connected teleoperated robotic systems play a key role in ensuring operational workflows are carried out with high levels of accuracy and low margins of error. In recent years, a variety of attacks have been proposed that actively target…
Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge…
With the rapid advancement and adoption of Audio Large Language Models (ALLMs), voice agents are now being deployed in high-stakes domains such as banking, customer service, and IT support. However, their vulnerabilities to adversarial…
In order to detect unknown intrusions and runtime errors of computer programs, the cyber-security community has developed various detection techniques. Anomaly detection is an approach that is designed to profile the normal runtime behavior…
Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the…
Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe,…
The increasing reliance on AI-driven 5G/6G network infrastructures for mission-critical services highlights the need for reliability and resilience against sophisticated cyber-physical threats. These networks are highly exposed to novel…
Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation…
This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…
The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing…
Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…
Function-calling language models are essential for agentic AI systems that translate natural language into executable structured actions, yet existing models exhibit severe structural instability when applied to Arabic. We present…
From software development to robot control, modern agentic systems decompose complex objectives into a sequence of subtasks and choose a set of specialized AI agents to complete them. We formalize agentic workflows as directed acyclic…
Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most…
The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin modern science. Molecular dynamics (MD) simulation presents a natural test bed to…
We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and…