Related papers: How does information access affect LLM monitors' a…
We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and services throughout the AI development lifecycle, from pre-deployment testing to post-deployment auditing. Combining principles from…
Large Language Models (LLMs) act as powerful reasoning engines but struggle with "symbol grounding" in embodied environments, particularly when information is asymmetrically distributed. We investigate the Privileged Information Bias (or…
While state-of-the-art large language models (LLMs) have shown impressive performance on many tasks, there has been extensive research on undesirable model behavior such as hallucinations and bias. In this work, we investigate how the…
The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions…
Edge intelligence delivers low-latency inference, yet most edge analytics remain hard-coded and must be redeployed as conditions change. When data patterns shift or new questions arise, engineers often need to write new scripts and push…
Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called…
In today's data-driven world, the proliferation of publicly available information raises security concerns due to the information leakage (IL) problem. IL involves unintentionally exposing sensitive information to unauthorized parties via…
Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional…
Information Extraction (IE) seeks to derive structured information from unstructured texts, often facing challenges in low-resource scenarios due to data scarcity and unseen classes. This paper presents a review of neural approaches to…
Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…
Automated evidence-based misinformation detection systems, which evaluate the veracity of short claims against evidence, lack comprehensive analysis of their adversarial vulnerabilities. Existing black-box text-based adversarial attacks are…
This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock…
LLM agents emit actions, not just text, and once taken, those actions often cannot be undone. Yet today's agent-safety evaluations run greedy or a few sampled rollouts and report a single safe/unsafe rate -- blind to the long-tail…
Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data…
The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models…
Vision-language models (VLMs) have advanced rapidly and are increasingly deployed in real-world applications, especially with the rise of agent-based systems. However, their safety has received relatively limited attention. Even the latest…
Numerous studies have shown that multimodal LLMs process speech and images well but fail in non-intuitive ways rendering trivial tasks such as object counting unreliable. We investigate this behavior from an information-theoretic…
Searchable Symmetric Encryption (SSE) allows users to search over encrypted data stored on untrusted servers, like cloud providers. While SSE hides the content of queries and documents, it still leaks patterns, such as how often a query is…
LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…
Traditional AI safety evaluations on isolated LLMs are insufficient as multi-agent AI ensembles become prevalent, introducing novel emergent risks. This paper introduces the Multi-Agent Emergent Behavior Evaluation (MAEBE) framework to…