New research on AI and security, selected for relevance to language models, AI agents and cybersecurity. Summaries are the authors’ or publisher’s own words, linked to the original.
Peer-reviewed
AI-guided human-in-the-loop inverse design of high performance engineering structures
New preprints (not yet peer-reviewed)
META-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM
Large Language Models (LLMs) remain vulnerable to jailbreak attacks and harmful-content prompts, particularly under adversarial distribution shifts where static alignment pipelines fail to generalize. Although introspective methods such as STAIR strengthen refusal consistency, they depend on fixed self-evaluation policies that cannot rapidly adapt to evolving manipulation strategies.
Understanding Efficient LLM Serving: An Empirical Study of Frameworks, Optimizations Algorithms, and Real-World Adoption
Large Language Models (LLMs) are integrated into software systems and AI services, making efficient LLM serving a concern for software engineering. Serving LLMs is challenging because inference requires computation, memory, GPU resources, and execution while maintaining latency and throughput.
MetaPI: Constructing Prompt Injection Benchmarks from LLM Agent Benchmark
Large language model (LLM) agents increasingly perform complex tasks using high-privilege tools, making indirect prompt injection (IPI) a critical security risk. However, IPI benchmarks lag behind their rapidly evolving utility counterparts, only offering limited task and environment coverage and relying on narrow, static attack scenarios.
Adversarial Evaluation of Large Language Models for Patient-Friendly Radiology Report Summarization
Purpose: To develop and validate a scalable adversarial evaluation framework for assessing the robustness of large language models (LLMs) that generate patient-friendly summaries of radiology reports. Methods: We introduced a clinically grounded adversarial framework that uses controlled term substitutions and impression removals across intensity levels.
Detecting Shadow AI: Unsanctioned LLM Agents on Enterprise Endpoints: A Taxonomy, an Open Detector and a Controlled Evaluation
Shadow IT, the use of technology that the IT organisation has not approved, is a long-standing governance problem. We argue that autonomous AI agents can make it grow much faster: agents make building tools nearly free, act with their user's privileges, and leave behind scripts, automations and MCP servers that are themselves unsanctioned.
Safety Direction Adapter: A Training-Free Post-Hoc Safety Patch for Fine-Tuned Open-Weight LLMs
Open-weight LLMs are routinely fine-tuned from public repositories, yet task-specific adaptation can silently erode safety alignment inherited from instruct-tuned bases. This is a supply-chain risk when organizations ship third-party checkpoints without full re-alignment.
CyberBinGym: Can AI Agents Turn Binary Patches into Real Exploits?
Security fixes usually reach users as compiled updates, but deployment delays leave unpatched systems exposed. During this window, comparing patched and unpatched binaries can reveal how to exploit a vulnerability, turning a defensive update into actionable information for attackers.
Enforcing Demographic Coherence: A Harms Aware Framework for Reasoning about Private Data Release
The technical literature about data privacy largely consists of two complementary approaches: formal definitions of conditions sufficient for privacy preservation and attacks that demonstrate privacy breaches. Differential privacy is an accepted standard in the former sphere.