OpenAI expands government footprint with AWS deal, report says
OpenAI has reportedly signed a partnership with AWS to sell its AI systems to the U.S. government for classified and unclassified work, marking an expansion beyond its Pentagon deal last month.
A Critical Analysis Of Rap Shield Laws
For years, scholars have been sounding the alarm on “rap on trial,” or the use of rap as evidence in criminal proceedings, pointing out that the fundamental characteristics of rap music make it uniquely susceptible to misinterpretation and prejudice. Scholars...
DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents
arXiv:2603.13791v1 Announce Type: new Abstract: Reliable detection of deceptive behavior in Large Language Model (LLM) agents is an essential prerequisite for safe deployment in high-stakes agentic contexts. Prior work on scheming detection has focused exclusively on black-box monitors that observe...
A Systematic Evaluation Protocol of Graph-Derived Signals for Tabular Machine Learning
arXiv:2603.13998v1 Announce Type: new Abstract: While graph-derived signals are widely used in tabular learning, existing studies typically rely on limited experimental setups and average performance comparisons, leaving the statistical reliability and robustness of observed gains largely unexplored. Consequently, it remains...
GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems
arXiv:2603.13940v1 Announce Type: new Abstract: While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive threat in which multiple agents...
A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems
arXiv:2603.13237v1 Announce Type: new Abstract: High-frequency banking environments face a critical trade-off between low-latency fraud detection and the regulatory explainability demanded by GDPR. Traditional rule-based and discriminative models struggle with "zero-day" attacks due to extreme class imbalance and the lack...
Feature-level Interaction Explanations in Multimodal Transformers
arXiv:2603.13326v1 Announce Type: new Abstract: Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision. Most existing multimodal explainable AI (MXAI) methods extend unimodal saliency to multimodal backbones, highlighting important tokens or patches within each modality,...
Developing and evaluating a chatbot to support maternal health care
arXiv:2603.13168v1 Announce Type: new Abstract: The ability to provide trustworthy maternal health information using phone-based chatbots can have a significant impact, particularly in low-resource settings where users have low health literacy and limited access to care. However, deploying such systems...
RTD-Guard: A Black-Box Textual Adversarial Detection Framework via Replacement Token Detection
arXiv:2603.12582v1 Announce Type: new Abstract: Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead deep learning models. While adversarial example detection offers a lightweight alternative to robust training, existing...
SpectralGuard: Detecting Memory Collapse Attacks in State Space Models
arXiv:2603.12414v1 Announce Type: new Abstract: State Space Models (SSMs) such as Mamba achieve linear-time sequence processing through input-dependent recurrence, but this mechanism introduces a critical safety vulnerability. We show that the spectral radius rho(A-bar) of the discretized transition operator governs...
Lyapunov Stable Graph Neural Flow
arXiv:2603.12557v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are highly vulnerable to adversarial perturbations in both topology and features, making the learning of robust representations a critical challenge. In this work, we bridge GNNs with control theory to introduce...
Truecaller now lets you hang up on scammers — on behalf of your family
Caller identity platform Truecaller recently launched a new feature that lets one person become an admin of a family group, get alerts about fraud calls received by other members, and even end a call on their behalf if they suspect...
RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents
arXiv:2603.11337v1 Announce Type: new Abstract: 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 pipeline...
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
arXiv:2603.11388v1 Announce Type: new Abstract: Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem where aligned...
CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks
arXiv:2603.12206v1 Announce Type: new Abstract: State space models (SSMs) like Mamba have gained significant traction as efficient alternatives to Transformers, achieving linear complexity while maintaining competitive performance. However, Hidden State Poisoning Attacks (HiSPAs), a recently discovered vulnerability that corrupts SSM...
Multilingual Financial Fraud Detection Using Machine Learning and Transformer Models: A Bangla-English Study
arXiv:2603.11358v1 Announce Type: new Abstract: Financial fraud detection has emerged as a critical research challenge amid the rapid expansion of digital financial platforms. Although machine learning approaches have demonstrated strong performance in identifying fraudulent activities, most existing research focuses exclusively...
Assessing Cognitive Biases in LLMs for Judicial Decision Support: Virtuous Victim and Halo Effects
arXiv:2603.10016v1 Announce Type: cross Abstract: We investigate whether large language models (LLMs) display human-like cognitive biases, focusing on potential implications for assistance in judicial sentencing, a decision-making system where fairness is paramount. Two of the most relevant biases were chosen:...
How to Count AIs: Individuation and Liability for AI Agents
arXiv:2603.10028v1 Announce Type: cross Abstract: Very soon, millions of AI agents will proliferate across the economy, autonomously taking billions of actions. Inevitably, things will go wrong. Humans will be defrauded, injured, even killed. Law will somehow have to govern the...
What crackdown? Trump's EPA enforcement claims don't pass sniff test.
75% of the criminal cases closed last fiscal year originated before Trump took office.
Bad Boy Jurisprudence
In 2009, President Barack Obama set off a “radioactive” debate when he told the White House Press Corps that he would seek a judge...The postBad Boy Jurisprudenceappeared first onHarvard Law Review.
United States v. Johnson
Drug detection dogs are critical tools in the fight against drug trafficking. However, law enforcement canines are imperfect: They sometimes incorrectly alert when performing...The post<em>United States v. Johnson</em>appeared first onHarvard Law Review.
$P^2$GNN: Two Prototype Sets to boost GNN Performance
arXiv:2603.09195v1 Announce Type: new Abstract: Message Passing Graph Neural Networks (MP-GNNs) have garnered attention for addressing various industry challenges, such as user recommendation and fraud detection. However, they face two major hurdles: (1) heavy reliance on local context, often lacking...
Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin
arXiv:2603.07286v1 Announce Type: new Abstract: Global safety models exhibit strong performance across widely used benchmarks, yet their training data rarely captures the cultural and linguistic nuances of Taiwanese Mandarin. This limitation results in systematic blind spots when interpreting region-specific risks...
Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning
arXiv:2603.07445v1 Announce Type: new Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a...
Leakage Safe Graph Features for Interpretable Fraud Detection in Temporal Transaction Networks
arXiv:2603.06632v1 Announce Type: new Abstract: Illicit transaction detection is often driven by transaction level attributes however, fraudulent behavior may also manifest through network structure such as central hubs, high flow intermediaries, and coordinated neighborhoods. This paper presents a time respecting,...
ERP-RiskBench: Leakage-Safe Ensemble Learning for Financial Risk
arXiv:2603.06671v1 Announce Type: new Abstract: Financial risk detection in Enterprise Resource Planning (ERP) systems is an important but underexplored application of machine learning. Published studies in this area tend to suffer from vague dataset descriptions, leakage-prone pipelines, and evaluation practices...
OpenAI and Google employees rush to Anthropic’s defense in DOD lawsuit
More than 30 OpenAI and Google DeepMind employees signed onto a statement supporting Anthropic's lawsuit against the Defense Department after the agency labeled the AI firm a supply-chain risk, according to court filings.
Anthropic sues Defense Department over supply-chain risk designation
Anthropic filed suit against the Department of Defense on Monday after the agency labeled it a supply-chain risk. The complaint calls the DOD's actions "unprecedented and unlawful."
Identifying Adversary Characteristics from an Observed Attack
arXiv:2603.05625v1 Announce Type: new Abstract: When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization) directly affect the ML models while others (e.g., anomaly detection) act within the broader...