arXiv:2608. 14692v1 Announce Type: cross Abstract: Personalized, generative AI systems increasingly adapt their behavior to individual users over time, fundamentally changing model behavior.
arXiv:2606. 09038v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories.
arXiv:2606. 30801v1 Announce Type: cross Abstract: Personalization algorithms determine what content users encounter on online platforms.
The study audits Bluesky’s Moderation Service (BMS) using its 10.6 million public moderation labels from 2025. It finds that BMS operates as a human‑AI collaboration: sexual and graphic content is flagged automatically in seconds, while more nuanced or high‑stakes content requires human review that can take hours or days. The system shows high precision (0.837) but low recall (0.222), with annotators detecting 4.5 times more harmful content than the system, and clustering reveals harms ranging from hostility toward protected groups to the spread of explicit material.
The paper argues that privacy in personalized AI should be viewed as a system-level issue rather than just a model-level one. It identifies four interconnected privacy‑risk channels in personalized AI and proposes four system‑level requirements—interaction trajectories, internal information flows, indirect leakage, and the privacy‑utility trade‑off—for evaluating privacy. The authors call for these requirements to be systematically incorporated into privacy audits of personalized AI systems.
Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks. However, the 'black-box' nature of these models, combined with the high dimensionality of multimodal cyber-physical data, poses significant interpretability challenges.
arXiv:2606. 02423v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm amplifiers that enable malicious users to achieve harmful outcomes beyond their capabilities through extended interactions.
arXiv:2608. 10434v1 Announce Type: new Abstract: Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks.
The paper introduces Safety Nudges, a browser-based tool that displays lightweight, in situ flags when a conversational AI exhibits risky behavior such as hallucination or overconfidence. In a two‑week field study with 45 frequent chatbot users, participants reported that the nudges were useful, clear, and minimally disruptive, and most felt more aware of potential AI harms. However, increased awareness did not automatically translate into measurable changes in user behavior, underscoring the need for relevance, calibration, and user control in nudge design.
Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static assessments, when supporting evidence is accessible at all. We present the Systemic Risk...
PersonaTeaming introduces a workflow that incorporates personas into adversarial prompt generation for generative AI, achieving higher attack success rates than the state‑of‑the‑art RainbowPlus while preserving prompt diversity. The system is extended into a user‑facing playground that lets red‑teamers create their own personas and collaborate with AI to refine prompts, fostering diverse strategies. A user study with 11 industry practitioners found the playground produced useful outputs and encouraged out‑of‑the‑box thinking, even when suggestions were not strictly followed.
The paper introduces the Systemic Risk Index, an open pipeline and dashboard that aggregates evidence from 19 public AI benchmarks into four systemic‑risk categories defined by the EU GPAI Code of Practice. It evaluates 18 models using harm‑preserving perturbations and simulated deployment contexts, offering users the ability to switch between average and worst‑case aggregation and to trace each risk rating back to its benchmark evidence. The study finds that worst‑case scores can be 14 to 37 points lower than average scores, and that LLM judges agree with human graders at a level comparable to human‑human agreement.
arXiv:2606. 00033v1 Announce Type: cross Abstract: While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments.