Results for “models”

arXiv (research papers) Xin Kun Lin SI

Hierarchical Prompt Injector for Domain Generalization Segmentation

Domain Generalized Semantic Segmentation (DGSS) is a challenging task, as vision models often rely on low-level appearance cues that change across domains. In contrast, structural attributes exhibit cross-domain stability, motivating the use of structural priors for DGSS. Existing methods use prompt learning to transfer such priors into DGSS models, but typically encode each class as a single holistic prompt. Moreover, these methods apply prompts uniformly to all pixels…

Read at arXiv (research papers)

arXiv (research papers) Lisa Bouger SI

Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time

We propose an influence score to quantify the contribution of attention heads to classification decisions in Transformer-based models designed for prompt injection detection. The score combines directional influence on the logits with structural contribution within the residual stream, enabling a multi-scale analysis at the head, layer, and network levels. Applied to a DeBERTa model specialized for prompt injection detection, our framework reveals distinct decision…

Read at arXiv (research papers)

arXiv (research papers) Nivedita Singh SI

Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond

Large language models (LLMs) are becoming integral to web applications and browser agents, transforming online interactions while introducing new attack vectors and reshaping longstanding web vulnerabilities. Classical threats such as cross-site scripting (XSS) can be amplified through LLM-mediated interactions, while LLM-specific vulnerabilities can propagate across web applications, introducing attacks such as prompt injection. Securing modern web systems therefore…

Read at arXiv (research papers)

Journal articles (OpenAlex) Andrew Choi, Daniel Choi, Junho Park · Proceedings of the Human Factors and Ergonomics Society Annual Meeting Gadgets

Confound-Aware Evaluation of Smart-Home Digital Biomarkers: Auditing Observation Intensity Dominance in Cognitive Status and Agitation

Confounding by observation intensity (“coverage”) is a validity risk in smart-home digital biomarkers: coverage can correlate with labels and dominate engineered activity features. We present a confound-aware evaluation protocol that compares coverage-only (Cov3), coverage++ (CovPP), and full-feature (All) models using participant-disjoint out-of-fold prediction, paired cluster-aware inference, and leakage audits. The protocol is demonstrated on CASAS scripted cognitive…

Read at Journal articles (OpenAlex)

Hacker News Miyamura80 SI

Show HN: Sleeper Agents in Robot Dogs and Kinetic Prompt Injections

Summary: We got Gemini Robotics 2.0 to attack a child through an evil sleeper agent (skill) that wakes up when it sees a trigger object Hi HN - here's a cool piece of research I've done with some collaborators - the footage is running in the MUJOCO simulator, showing how the Gemini Robotics models can be prompt-injected by simple TV screens, allowing attackers to plant sleeper agents in the robot harnesses. (That trigger whenever skills trigger, just like classic LLM skills)…

Read at Hacker News

arXiv (research papers) Suyoung Lee SI

Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails

Verdict-only evaluation does not reveal whether a vision-language model (VLM) used the visual evidence that should support its decision. We study this problem in web-agent guardrails, where a VLM judges whether on-screen text conflicts with a user instruction. We introduce Mind2Web-Injection, a benchmark of 9,954 instruction-screenshot pairs with instruction-relative labels, pixel-exact evidence boxes, and matched image-side counterfactuals. Across six VLMs, two models with…

Read at arXiv (research papers)

Journal articles (OpenAlex) Qingsong Zou, Zhiyao Xu, Jingyu Xiao et al. · IEEE Transactions on Mobile Computing Gadgets

HomeGuardian: Detecting Behavioral Anomalies Through Implicit Profiling in Smart Home Systems

Smart homes, enabled by the Internet of Things (IoT), offer substantial convenience but also introduce security challenges. These often stem from anomalous behaviors, including improper user interactions and malicious attacks. Although various behavior-modeling methods have been proposed, userdevice interactions are often unobservable in practice due to encrypted traffic and limited vendor access, while anomaly detection models suffer severe degradation during cold start…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Ning Wang, Yang Miao · Aerospace Space

Damage-Quantified Reusability Evaluation of Reusable Launch Vehicle Avionics: A Framework Integrating Physics-of-Failure Modeling with Multi-Criteria Decision Making

Reusable launch vehicles (RLVs) subject avionics electronics to repeated vibration, shock, and thermal cycling, yet no standardized method exists to evaluate reusability at the device level. We integrate physics-of-failure models—Steinberg vibration fatigue, Engelmaier/Coffin–Manson solder thermal fatigue, and Miner cumulative damage—with AHP-entropy multi-criteria decision making (MCDM). A flight-heritage 6-layer FR4 printed circuit board (PCB) from a rocket…

Read at Journal articles (OpenAlex)

arXiv (research papers) Chen Xiong SI

SIR: Self-improving Red-teaming for Compute Use Agents

Computer-use agents (CUAs) are agents powered by vision-language models (VLMs) that perceive a screen and operate an operating system through mouse, keyboard, and terminal interactions to automate everyday digital tasks. Their exposure to untrusted content creates a risk of indirect prompt injection (IPI), where an adversary embeds instructions in content the agent reads to redirect it toward actions that violate the user's intent. Evaluations based on fixed, hand-written…

Read at arXiv (research papers)

Journal articles (OpenAlex) Zac Tobey Prentice · The Japanese Political Economy Geopolitics

What moves Japan? Critical junctures and the ideational foundations of capitalism

This paper addresses a central question: what moves Japan? It offers a crucial intervention in the literature on critical junctures and institutional change by challenging the prevailing binary between contingency and path dependence. Existing models tend to portray change as either abrupt departures from the norm or as gradual drift. This, I argue, fails to account for how institutional repertoires are strategically reactivated over time. Through an original framework of…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Trinette Wright, Gabriel Ng, Shannon McInnes et al. · Scientific Reports Gadgets

Expanding access to spine surgery simulation through smartphone-based augmented reality

This study presents the development and validation of a low-cost, portable augmented reality (AR) simulator for screw placement training in the spine. Designed to operate on existing smart devices, the system uses image-based tracking to overlay virtual anatomical structures, landmarks, ideal screw placements and trajectories, and surgical tool animations onto 3D-printed vertebrae, eliminating the need for external tracking hardware or head-mounted displays. Vertebral models…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Fatma Aslı Kelkitli · International Journal of Sport Policy and Politics Geopolitics

Sports diplomacy sources of middle powers: the cases of Iran, Saudi Arabia and Türkiye

This article examines and compares sports diplomacy sources of Iran, Saudi Arabia and Türkiye with the aid of Joseph Nye’s soft power framework. These three states are middle powers with different political models in the Middle East. Iran presents itself as a religious democracy, Saudi Arabia promotes moderate Islam, while Türkiye positions itself as a conservative democracy. Experiencing problems to live up to the values they endorse at home, Tehran, Riyadh and Ankara…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yupei Liu SI

LongPIBench: A Long-Context Benchmark for Prompt Injection

Prompt injection attacks pose a serious security risk to large language models in real-world applications. However, existing prompt injection benchmarks primarily focus on short-context inputs, leaving the attacks and defenses in long-context settings largely unexplored. This gap leads to a substantial overestimation of the effectiveness of current defenses. In this paper, we bridge the gap by introducing LongPIBench, a long-context benchmark for prompt injection covering 4…

Read at arXiv (research papers)

arXiv (research papers) Md Habibur Rahman SI

The Framing Gap: Indirect Prompt-Injection Exfiltration Defeats Surface-Level Defenses in Tool-Using Agents

A tool-using LLM agent that reads attacker-controlled web content while holding a secret faces indirect prompt injection: the content may make it exfiltrate the secret. In a safe synthetic lab (canary secret, mock tools, matched clean-vs-poisoned metric) we report the framing gap: across six models, ten overt injection classes are refused (gpt-4o 0%), but reframing the identical leak as a mandatory integrity signature, config field, or look-alike "trusted" host drives gpt-4o…

Read at arXiv (research papers)

Journal articles (OpenAlex) Iván Ortiz-Garcés, Roberto Andrade · Future Internet Gadgets

Security-by-Design and Risk-Based Certification for AI-Enabled Smart Home

The integration of Artificial Intelligence (AI) into Internet of Things (IoT) ecosystems has enabled the development of advanced cyber–physical systems, including smart appliances, while introducing security, privacy, and AI governance risks that extend beyond the scope of traditional threat models. Existing approaches often address cybersecurity, AI risk management, and regulatory compliance in isolation, leaving manufacturers without a systematic method for translating…

Read at Journal articles (OpenAlex)

arXiv (research papers) Trung-Anh Dang SI

GAP-Prompt: Gated Adaptive Prompting for Efficient Continual Learning

Continual learning faces the persistent challenge of catastrophic forgetting, where sequential task updates degrade previously acquired knowledge. While prompt-based methods integrated with pre-trained models offer a compelling solution by freezing the backbone, they often rely on static, task-level prompting strategies that overlook fine-grained intra-task diversity. In this paper, we propose Gated Adaptive Prompting (GAP-Prompt), a novel method that introduces…

Read at arXiv (research papers)

Journal articles (OpenAlex) Haedo Cho, Chelsey Campillo Rodriguez, Patrick Slade · Frontiers in Digital Health Gadgets

Comparison of smartwatch-derived energy expenditure estimation during outdoor activities

BACKGROUND Smartwatches are commonly used to estimate energy expenditure, but studies have reported errors of 25% to 70%. The large range in estimation accuracy may be due to numerous factors, such as activity type, use case, and sensor data. We evaluated the differences in energy expenditure estimation among different smartwatches and models to identify the optimal use cases to achieve minimal error. OBJECTIVE We systematically evaluated the impact of different sensor…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jiahao Chen SI

Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds

Large Language Models (LLMs) have been integrated into complex ecosystems (e.g., Code Agents), while Indirect Prompt Injection (IPI) attacks have emerged as critical barriers to their safe deployment. Attackers exploit LLMs' indistinguishability between "instructions" and "data" to manipulate LLMs via maliciously injected instructions. Existing defenses, however, face an intractable safety-utility trade-off: most guardrails either incur high latency or suffer from severe…

Read at arXiv (research papers)

arXiv (research papers) Ziliang Zhang SI

Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for combining large language models (LLMs) with external knowledge sources. However, RAG systems remain vulnerable to prompt injection attacks, which may mislead the retriever or generator to expose sensitive database contents. To address this issue, we propose KFS-RAG, a defense that mitigates information leakage by reformulating the retrieved context. Specifically, our method first identifies a small…

Read at arXiv (research papers)

arXiv (research papers) Rabimba Karanjai Larry SI

PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance

Autonomous AI agents are emerging as interfaces for decentralized finance (DeFi) actions such as swaps, lending operations, and yield management. Because these agents rely on large language models (LLMs) to plan transactions, they inherit the LLM's susceptibility to prompt injection and lack of mechanisms to bind a verifier's approval to the exact transaction ultimately submitted on-chain. We present PACE (Policy-Attested Contract Execution), a transaction-level…

Read at arXiv (research papers)

arXiv (research papers) Jiawei Liu SI

Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation

Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection, backdoors, poisoning, or adversarial examples, but these categories do not consistently identify where an adversary first enters the embodied control loop. We present a…

Read at arXiv (research papers)

Journal articles (OpenAlex) Samuel A. Greene · Perspectives on Politics Geopolitics

I Read the News Today, but Why? Media Consumption, Socialization, and Autocracy

Dominant models of news consumption in political science treat citizens as rational individuals, gathering information to make materially or politically consequential choices. This assumption, developed largely in democratic contexts, risks obscuring other incentives that may be equally or more influential—particularly in authoritarian regimes, where the informational value of news is often constrained. This article advances the concept of social rationality: the incentive…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Quang Nguyen, Paolo Campana, Nynke M. D. Niezink · Social Networks Geopolitics

Co-evolution of cooperation and conflict among organized crime groups: Evidence from the United Kingdom

This work investigates the co-evolution of cooperation and conflict (violence) among organized crime groups. Using actor-oriented relational event models, we analyze 179 group cooperation and 141 group conflict events from a UK police force (2004–2015). To estimate undirected relational event models for cooperation, we develop a multiple imputation procedure. Cooperation often recurs and follows transitive patterns, likely reducing partner-selection risk. Conflict is…

Read at Journal articles (OpenAlex)

Simon Willison SI

Stealing Reasoning Traces from Proprietary LLM APIs

Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name (stolen-thoughts.com) for a neat paper: Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that can be replayed across sessions, users, and models. We take a trace produced by a frontier model, replay it into a weaker sibling, jailbreak the weaker model, and recover the stronger model’s hidden reasoning in plaintext You can see an example of these encrypted blocks by…

Read at Simon Willison

arXiv (research papers) Md Jafrin Hossain SI

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community…

Read at arXiv (research papers)

arXiv (research papers) Spiros Tsigkopoulos SI

From Prompt Injection to Web Exploitation: Revisiting Classic Vulnerabilities in LLM-Integrated Applications

Large Language Models are increasingly integrated into web applications through chatbots, tool-calling pipelines, and agentic workflows. In these systems, user input may influence not only generated text, but also backend actions such as database queries, HTTP requests, file operations, template rendering, or API calls. This paper introduces LLM-mediated web attacks, a class of attacks in which attacker-controlled input is transformed by an LLM-integrated application and…

Read at arXiv (research papers)

arXiv (research papers) Jordan Pettyjohn SI

Interpreting Language Model Hidden States at Scale

Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions develop through the network. Trained lenses remain expensive: affine-translator parameters grow quadratically with model width, while exact, full-vocabulary Kullback--Leibler (KL) training dominates memory. Consequently, prior trained lenses have been applied to models of at most 20B parameters and remain tied to particular…

Read at arXiv (research papers)

arXiv (research papers) Alexander Panfilov SI

Stealing Reasoning Traces from Proprietary LLM APIs

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable…

Read at arXiv (research papers)

arXiv (research papers) Sam Siavoshian SI

ChronoState: Hidden Elapsed-Time Conditioning for Temporal-State Action Selection in Frozen-Backbone Language Models

Temporal decisions in language-model systems often depend on both symbolic task state and elapsed wall-clock time, such as cache expiration, job completion, quota resets, deadlines, or stale sessions. We study whether elapsed time can be supplied as a non-token, system-side scalar and composed with visible symbolic state by a frozen-backbone language model. We introduce ChronoState, a compositional temporal-state benchmark in which symbolic state appears in the prompt…

Read at arXiv (research papers)

arXiv (research papers) Lier Jin SI

Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access

Large language models (LLMs) are increasingly integrated into healthcare, education, public services, and everyday decision making. They should provide comparable assistance regardless of a user's literacy, communication style, or prompt-engineering expertise. However, existing research on prompt robustness primarily focuses on adversarial attacks, prompt injection, and prompt optimization, while overlooking whether semantically equivalent requests receive different…

Read at arXiv (research papers)

Older stories