Transparency

Autonomous driving planning requires translating navigation intent, traffic rules, dynamic interactions, and language instructions into executable continuous trajectories. Vision-Language-Action models have been introduced into driving planning to improve long-tail generalization, commonsense reasoning, high-level semantic understanding, and explainability. However, existing VLA planners mainly follow planning-head-based trajectory prediction or full-trajectory autoregressive generation. The for

Explainability is central to building trustworthy AI, yet explanation interfaces can inadvertently provide adversaries with an expanded privacy-related attack surfaces. Recent studies show that advanced membership-inference attacks succeed by exploiting confidence-drop trajectories, induced through attribution-guided perturbations, as discriminative features, rather than directly using confidence scores or explanation vectors. Existing defenses against membership inference fail to directly mitig

As artificial intelligence (AI) systems become more integrated into decision-making processes, the need for explainability has emerged to foster trust, understanding, and effective human-AI collaboration. With the variety of explainable AI (XAI) methods available, selecting the right one for a specific user group and a given use case remains challenging, especially given the limited empirical validation of existing theoretical guidance. This systematic literature review addresses this gap by syn

This letter provides GAO's comments on the American Institute of Certified Public Accountants (AICPA) Auditing Standards Board's (ASB) Proposed Statement on Standards for Attestation Engagements: Common Concepts, Examination Engagements, Review Engagements, and Engagements to Report on Sustainability Information and Proposed Statement on Standards for Attestation Engagements: Amendments to SSAE Nos. 18-19 and 21 to Reflect Proposed SSAE Common Concepts, Examination Engagements, Review Engagement

Ensuring model reliability in Explainable AI requires a global assessment of the hypothesis space. We propose a formal framework for the exhaustive analysis of optimal and near-optimal decision trees, called Algebraic Decision Tree Counting (ADTC). Inspired by Algebraic Model Counting (AMC) in knowledge representation, ADTC reformulates diverse analytical tasks, such as optimization, counting, and sampling, into a unified sum-of-products computation over a semiring $R$. While the hypothesis spac

New EU AI guidance sets practical expectations for labelling, deepfakes and AI-generated content transparency. In Brief Companies are increasingly using AI to create or modify content across marketing, communications and customer-facing channels. As EU transparency obligations under the AI Act move closer to application, this raises practical and operational questions around when AI-generated or AI-manipulated [...] The post New EU guidance on AI transparency: what should companies be doing from

Long-running adaptive intelligent agents face a structural tension between knowledge consolidation and information integrity. Memory consolidation is conventionally treated as an agent-changing operation: a model is fine-tuned, a prompt rewritten, a policy distilled, or a reflection appended to the context that governs future behaviour. In regulated autonomic deployment this is a liability because the agent operates under commitments and audit contracts that bind to a specific, cryptographically

This work introduces AIriskEval-edu-db2, a new dataset designed to train and evaluate auditors based on LLMs for an explainable pedagogical risk assessment in instructional content for grades K-12. The dataset comprises 1,639 explanations from 170 curated ScienceQA questions, covering science, language arts, and social sciences. For each question, the dataset includes an explanation written by a human teacher alongside 11 explanations generated by LLM-simulated teacher profiles associated with d

CSET’s Jessica Ji shared her expert insight in an article published by WIRED. The article examines the launch of FLARE-AI, a new crowdsourced platform designed to improve transparency and accountability by creating a centralized system for reporting harmful AI behavior and model flaws. The post You Can Now Sound the Alarm on AI Behaving Badly appeared first on Center for Security and Emerging Technology .

Engineering management research has produced mature frameworks for software risk: ownership by feature, escalation by severity, and assurance by test coverage. These frameworks implicitly assume deterministic behavior, discrete and auditable change events, and clear component-to-owner mappings. Teams that build and operate agentic AI systems violate all three assumptions at once: outputs are probabilistic, systems take autonomous multi-step actions, and the risk surface mutates silently between

Digital forensic investigations of network intrusions require analytical outputs that are traceable, reproducible, and court-defensible - requirements existing machine learning pipelines do not satisfy, since they treat original evidence as training data and produce opaque classifications without instance-level justification. This paper presents a forensic-oriented intrusion detection framework resolving both problems simultaneously, integrating synthetic data generation, binary classification,

Flaw Reporting for AI (FLARE-AI) allows developers and security researchers to submit artificial intelligence flaws for formal, coordinated disclosure.

A court in Germany found that Google was responsible for what its chatbots say in search summaries. This is the accountability we need.

Explainable AI (XAI) methods have demonstrated significant success in recent years at identifying relevant features in input data that drive deep learning model decisions, enhancing interpretability for users. However, the potential of XAI beyond providing model transparency has remained largely unexplored in adjacent machine learning domains. In this paper, we show for the first time how XAI can be utilized in the context of federated learning. Specifically, while federated learning enables col

Medical Artificial Intelligence (AI) is widely expected to transform clinical practice, yet the decision-making processes of many Machine Learning (ML) models remain opaque. Explainability has been advanced as a partial remedy to clarify why AI generates predictions, particularly in high-stakes contexts. Despite ongoing efforts, debates on what constitutes an adequate medical explanation remain unsettled. Yet, explanation has long been a central topic of inquiry in the philosophy of science and

Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety. Yet the AI reporting ecosystem is fragmented: researchers who identify flaws often do not know what or where to report, and groups who receive reports rarely share them with other relevant stakeholders. As a result, good-faith reporters duplicate effort by submitting many different forms, and recipients lack standardized, triage-ready information. We audit 12 reporting systems published

Since the Leveson Report was published in 2012, exposing a collapse in ethical standards across the press, most national newspapers have adopted a similar stance: objection to the very principle of accountability. They believe that while social media, broadcast media and every other industry should be regulated, they alone should be permitted to operate and […]

Reducing compensation to symbolic amounts strips the regulation of its primary purpose: consumer protection and accountability.

Large language models (LLMs) increasingly participate in communicative practices that resemble human interaction: users ask them questions, rely on their outputs for belief formation and action guidance, and sometimes develop affective attachments. These practices raise a central philosophical question: can the outputs of LLMs be regarded as assertions, and if so, what follows for responsibility and accountability? Standard theories of assertion and testimony assume that assertions require asser

External evaluations are becoming increasingly central to the governance of AI systems. In practice, however, independent auditors often have limited access to deployed models and must rely on query-based interactions. Most existing fairness evaluation methods assume static datasets and fixed-sample statistical tests, making them poorly suited to real-world auditing scenarios in which evidence must be collected sequentially under query constraints. In this work, we formulate fairness auditing as

Always-on agents are systems whose future behavior depends on durable state accumulated across earlier interactions. We treat them as persistent-state systems: the operative system includes retrievable memories, but also task ledgers, permissions, credentials, commitments, provenance and audit records, shared state, trigger conditions, and externally committed effects linked to those records. The survey reads the literature through six diagnostic axes for each state item, authority, scope, mutab

LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify. This paper combines a hybrid survey - a systematic search paired with narrative synthesis and separately tracked grey evidence - with a conceptual framework and a structured ten-model audit. The synthesis spans eight evidence streams: benchmark validity, dynamic evaluatio

Parliament gives final approval to the digital omnibus and a "nudifier" ban, while the Commission rolls out labelling icons and FAQs for the AI-generated content transparency Code.

Cardiac discharge phenotyping informs post-discharge treatment and follow-up, but real-world records are often incomplete and class-imbalanced, increasing the risk of missed high-risk phenotypes. We propose CW-B, a clinical risk-aligned class-weighted XGBoost pipeline for five-class cardiac discharge phenotyping under real-world class imbalance and missingness. CW-B combines fold-specific class-balanced instance weighting, missingness-indicator augmentation, and classwise error auditing to impro

Machine learning network intrusion detection systems (IDS) rely on aggregate flow statistics that discard distributional structure, while established entropy measures require raw packet sequences unavailable in pre-aggregated flow datasets. We propose Multi-Level Distributional Entropy (MDE), an analytical framework that derives interpretable entropy features directly from flow-level summary statistics at three levels: within-flow Gaussian differential entropy, cross-directional Jensen-Shannon d

Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary labels, leaving agents unable to self-correct and operators unable to audit. We present SEVA, a structured verification agent that emits evidence alignments, step-by-step reasoning chains, calibrated confidence, and a six-category error diagnosis with actionable fixes. Training such an agent with RL is non-trivial: standard

This paper presents a systematic review and meta-analysis of 62 studies that developed speech- and language-based AI for severe mental illnesses (SMI) (i.e., characterized by substantial communication problems affecting speech production and language). We employed a random-effects meta-analysis using Restricted Maximum Likelihood (REML). We evaluated these studies using our proposed rigorous 16-item quality assessment framework, grouped into three domains: Study Design, Fairness and Explainabili

Enhanced transparency and exchange of information to put an end to bank secrecy and fight tax evasion and avoidance ...

The advance of these technologies is not occurring as an exception. They are established silently, without public debate, without transparency and without people knowing the fate of their data

We ask under what conditions an agent with a harm-minimizing policy can displace an approval-seeking (RLHF) agent in a competitive market, and when that policy is sufficient to prevent community harm. We use evolutionary game theory (finite-population Moran-Fermi pairwise comparison) to formalize this subject to assumptions of wisher hindsight, peer testimony, a monotone harm ledger, sufficient information density of community feedback, and a finite, depleting resource pool, in a negative-sum en

In brief Organizations that develop or deploy AI agents – autonomous systems that can pursue goals and take actions with limited human intervention – are navigating a rapidly evolving US legal landscape that pulls agentic AI under laws that govern action. Emerging legal developments support the view that accountability generally runs to the humans and [...] The post US Legal Accountability for AI Agents: When AI agents act, who is responsible under US laws? appeared first on Connect On Tech .

Speech-based cognitive impairment detection offers a noninvasive, accessible alternative to costly biomarker assays, yet transformer-based models remain clinically uninterpretable. We propose a multi-stage explainability framework that translates black-box transformer predictions into clinically grounded narratives by integrating SHapley Additive exPlanations (SHAP)-based token attribution, theory-informed linguistic features, and a four-stage LLM reasoning pipeline using LLaMA-3.1-70B-Instruct.

Artificial intelligence is transforming biodiversity monitoring by enabling automated analysis of ecological imagery collected from camera traps, drones, satellites, underwater platforms, and other sensing systems. These tools can expand the scale and speed of conservation assessments, yet many computer vision models remain difficult to inspect, making it challenging to determine whether predictions are based on ecologically meaningful signals or on spurious correlations, sampling biases, and ot

Seeking transparency and accountability in Paraguay’s use of facial recognition, EFF, the Association of Technology, Education, Development, Research, Communication (TEDIC), and the Centre for Justice and International Law (CEJIL) filed a complaint with the Inter-American Commission on Human Rights against the state for arbitrarily denying access to information about its implementation and use of the technology as a tool for mass surveillance that erodes people’s privacy rights. The case involve

Modern AI systems are increasingly deployed under non-stationary computational, demographic, and operational conditions in which static resource allocation strategies degrade both predictive performance and human-centric properties such as fairness and explainability. This paper presents AURORA-AI, an Adaptive Utility-driven Resource Orchestration framework for Resilient AI that unifies Hamilton-Jacobi-Bellman feedback control, Lyapunov-based stability monitoring, and a fairness-aware composite

Large language models (LLMs) are increasingly being integrated into mental health support tools and other psychologically sensitive conversational applications. In such settings, behavioral stability and consistency are important for trustworthy human-AI interaction. However, semantically similar concerns can be presented through different contextual framings, potentially eliciting different model responses. Such framing-sensitive variability may challenge user expectations regarding system beha

Automatic Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in multilingual and demographically diverse Indian healthcare context remains largely unknown. In this study, we first conduct the systematic audit of ASR performance on real-world psychiatric interview data spanning Kannada, Hindi and Indian English, comparing eight state-of-the-art models including IndicWhisper, WhisperLargeV3, Sarvam, GoogleS2T, Gemma3n, OmniLingual, Vaani, and Gemini.

Concept Bottleneck Models (CBMs) promise transparent reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamentally depends on how well visual and textual representations are aligned or matched. Existing vision-language CBMs often rely on pre-aligned encoders or global cosine similarity, which obscures fine-grained concept localization and fails to reflect true semantic geometry. In this work, we rethink concept alignment as a dynamic cross-modal transport pr

Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization. This work presents NebulaExp, a fully transparent, ablation-driven post-training pipeline built on Qwen3-8B-base, covering two orthogonal model branches: general instruct model and complex reasoning-special

Medical AI remains organized around isolated models, whereas care requires accountable capabilities that persist across time. We define clinical AI skills and propose the Clinical Harness, a runtime governance architecture that registers, orchestrates, constrains and monitors them. Using osteoporosis as an exemplar, we show how knowledge-driven, data-driven and physics-enhanced skills can support lifecycle care and provide a governed substrate for future medical agents.