Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
arXiv:2603.03725v1 Announce Type: new Abstract: The volume of freely scraped data on the Internet has driven the tremendous success of deep learning. Along with this comes the growing concern about data privacy and security. Numerous methods for generating unlearnable examples...
LEA: Label Enumeration Attack in Vertical Federated Learning
arXiv:2603.03777v1 Announce Type: new Abstract: A typical Vertical Federated Learning (VFL) scenario involves several participants collaboratively training a machine learning model, where each party has different features for the same samples, with labels held exclusively by one party. Since labels...
Structure-Aware Distributed Backdoor Attacks in Federated Learning
arXiv:2603.03865v1 Announce Type: new Abstract: While federated learning protects data privacy, it also makes the model update process vulnerable to long-term stealthy perturbations. Existing studies on backdoor attacks in federated learning mainly focus on trigger design or poisoning strategies, typically...
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models
arXiv:2603.02482v1 Announce Type: cross Abstract: Safety evaluation and red-teaming of large language models remain predominantly text-centric, and existing frameworks lack the infrastructure to systematically test whether alignment generalizes to audio, image, and video inputs. We present MUSE (Multimodal Unified Safety...
Anthropic CEO Dario Amodei calls OpenAI’s messaging around military deal ‘straight up lies,’ report says
Anthropic gave up its contract with the Pentagon over AI safety disagreements -- then, OpenAI swooped in.
The US military is still using Claude — but defense-tech clients are fleeing
As the U.S. continues its aerial attack on Iran, Anthropic models are being used for many targeting decisions.
BLUFF: Benchmarking the Detection of False and Synthetic Content across 58 Low-Resource Languages
arXiv:2603.00634v1 Announce Type: new Abstract: Multilingual falsehoods threaten information integrity worldwide, yet detection benchmarks remain confined to English or a few high-resource languages, leaving low-resource linguistic communities without robust defense tools. We introduce BLUFF, a comprehensive benchmark for detecting false...
The justices’ troubling message to lower courts
Civil Rights and Wrongs is a recurring series by Daniel Harawa covering criminal justice and civil rights cases before the court. In two recent decisions, the Supreme Court summarily reversed […]The postThe justices’ troubling message to lower courtsappeared first onSCOTUSblog.
Detoxifying LLMs via Representation Erasure-Based Preference Optimization
arXiv:2602.23391v1 Announce Type: new Abstract: Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful continuations, but...
ChatGPT uninstalls surged by 295% after DoD deal
Many consumers ditched ChatGPT's app after news of its DoD deal went live, while Claude's downloads grew.
No one has a good plan for how AI companies should work with the government
As OpenAI transitions from a wildly successful consumer startup into a piece of national security infrastructure, the company seems unequipped to manage its new responsibilities.
Tech workers urge DOD, Congress to withdraw Anthropic label as a supply-chain risk
Tech workers have signed an open letter urging the Department of Defense to withdraw its designation of Anthropic as a "supply chain risk" and instead to settle the matter quietly.
Expressive Association as Shield, not Sword: A Constitutional Defense of DEI
Introduction Diversity, equity, and inclusion (DEI)—an effort aimed at remedying historic inequality in opportunities—faces the chopping block. Its opposition claims it commits the very sin it aimed to rid: discrimination. DEI’s opposition has mobilized and attacked on all fronts, already...
ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
arXiv:2602.20708v1 Announce Type: new Abstract: Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution. Existing defenses typically rely on strict filtering or refusal mechanisms, which suffer...
Beyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive Information
arXiv:2602.21496v1 Announce Type: new Abstract: While defenses for structured PII are mature, Large Language Models (LLMs) pose a new threat: Semantic Sensitive Information (SemSI), where models infer sensitive identity attributes, generate reputation-harmful content, or hallucinate potentially wrong information. The capacity...
Bounded Rationality and the Theory of Property
ARTICLE Bounded Rationality and the Theory of Property Oren Bar-Gill* & Nicola Persico** Strong, property rule protection—implemented via injunctions, criminal sanctions, and supercompensatory damages—is a defining aspect of property. What is the theoretical justification for property rule protection? The conventional...
OpenAI reveals more details about its agreement with the Pentagon
By CEO Sam Altman’s own admission, OpenAI’s deal with the Department of Defense was “definitely rushed,” and “the optics don’t look good.”
Fintech Regulation 2026: Navigating the New Compliance Landscape
The regulatory environment for fintech has evolved dramatically, with new frameworks addressing digital assets, open banking, and AI-driven financial services.
Autonomous Vehicles and Liability: Who Is Responsible When AI Drives?
As autonomous vehicles approach widespread deployment, legal frameworks for determining liability in accidents involving self-driving cars remain uncertain.
A Systematic Review of Algorithmic Red Teaming Methodologies for Assurance and Security of AI Applications
arXiv:2602.21267v1 Announce Type: cross Abstract: Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While red teaming has long been recognized as an effective method to identify vulnerabilities by simulating...
Bankruptcy as a National Security Risk lawreview - Minnesota Law Review
By JASON JIA-XI WU. Full Text. Defense contractors lie at the heart of the U.S. national security regime. Each year, over half of the federal defense budget is allocated to contracts outsourcing military operations, projects, and services to private companies....
Trump moves to ban Anthropic from the US government
The Defense Department pressured Anthropic to drop restrictions on how its AI can be used by the military.
OpenAI’s Sam Altman announces Pentagon deal with ‘technical safeguards’
OpenAI's CEO claims its new defense contract includes protections addressing the same issues that became a flashpoint for Anthropic.
Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
arXiv:2602.23079v1 Announce Type: new Abstract: The rapid advancement of large language models (LLMs) has enabled powerful authorship inference capabilities, raising growing concerns about unintended deanonymization risks in textual data such as news articles. In this work, we introduce an LLM...
Court rules criminal defendants may be prohibited from discussing ongoing testimony with counsel during an overnight recess
When a trial court recesses a criminal trial during a defendant’s testimony, the court may order the defendant and his lawyer not to discuss that testimony during the break except […]The postCourt rules criminal defendants may be prohibited from discussing...
CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense
arXiv:2602.20418v1 Announce Type: new Abstract: Graph neural networks (GNNs) have demonstrated superior performance in various applications, such as recommendation systems and financial risk management. However, deploying large-scale GNN models locally is particularly challenging for users, as it requires significant computational...
CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks
arXiv:2602.20419v1 Announce Type: new Abstract: Machine Learning as a Service (MLaaS) has emerged as a widely adopted paradigm for providing access to deep neural network (DNN) models, enabling users to conveniently leverage these models through standardized APIs. However, such services...
In Defense of Substantive Due Process
Introduction Originalism has a branding and substance problem.[1] If originalism is what it purports to be—impartial and value-free enforcement of the Founders’ intention and “the only approach to text that is compatible with democracy”[2]—more Americans would have faith in the...
Anthropic won’t budge as Pentagon escalates AI dispute
The Pentagon has given Anthropic until Friday to loosen AI guardrails or face potential penalties, escalating a high-stakes dispute that raises questions about government leverage, vendor dependence, and investor confidence in defense tech.
Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
arXiv:2602.17778v1 Announce Type: new Abstract: Multi-turn interaction length is a dominant factor in the operational costs of conversational LLMs. In this work, we present a new failure mode in conversational LLMs: turn amplification, in which a model consistently prolongs multi-turn...