搜索结果：Guardian

Safety filtering is an effective method for enforcing constraints in safety-critical systems, but existing methods typically assume perfect state information. This limitation is especially problematic for systems that rely on neural network (NN)-based state estimators, which can be highly sensitive to noise and adversarial input perturbations. We address these problems by introducing GUARDIAN: Guaranteed Uncertainty-Aware Reachability Defense against Adversarial INterference, a safety filtering framework that provides formal safety guarantees for systems with NN-based state estimators. At runtime, GUARDIAN uses neural network verification tools to provide guaranteed bounds on the system's state estimate given possible perturbations to its observation. It then uses a modified Hamilton-Jacobi reachability formulation to construct a safety filter that adjusts the nominal control input based on the verified state bounds and safety constraints. The result is an uncertainty-aware filter that ensures safety despite the system's reliance on an NN estimator with noisy, possibly adversarial, input observations. Theoretical analysis and numerical experiments demonstrate that GUARDIAN effectiv

Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yielding safer-on-paper yet less useful systems. This work introduces Guardian-as-an-Advisor (GaaA), a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference, keeping the base model operating under its original spec. To support training and evaluation, GuardSet is constructed, a 208k+ multi-domain dataset unifying harmful and harmless cases with targeted robustness and honesty slices. GuardAdvisor is trained via SFT followed by RL to enforce label-explanation consistency. GuardAdvisor attains competitive detection accuracy while enabling the advisory workflow; when used to augment inputs, responses improve over unaugmented prompts. A latency study shows advisor inference uses below 5% of base-model compute and adds only 2-10% end-to-end overhead under realistic harmful-input rates. Overall, GaaA steers models to comply with the model spec, maintaining safety while reducing over-refusal.

Guardian models play a crucial role in ensuring the safety and ethical behavior of user-facing AI applications by enforcing guardrails and detecting harmful content. While standard guardian models are limited to predefined, static harm categories, we introduce DynaGuard, a suite of dynamic guardian models offering novel flexibility by evaluating text based on user-defined policies, and DynaBench, a dataset for training and evaluating dynamic guardian models. Our models provide both rapid detection of policy violations and a chain-of-thought reasoning option that articulate and justify model outputs. Critically, DynaGuard not only surpasses static models in detection accuracy on traditional safety categories, but is competitive with frontier reasoning models on free-form policy violations, all in a fraction of the time. This makes DynaGuard an critical tool for language model guardrails.

Guardian maps are scalar maps that vanish when a matrix or polynomial is on the verge of stability. Several guardian maps have been proposed in the literature for Hurwitz stability based on the Kronecker sum, the second lower Schläflian matrix, and the bialternate sum. It is natural to ask if there is a unifying principle for all these maps. Here, we introduce the Lie-algebraic notion of a guardian representation, and show that all the examples above are instances of this unifying idea. We also show that the bialternate sum coincides with the second additive compound.

We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM). These models offer comprehensive coverage across multiple risk dimensions, including social bias, profanity, violence, sexual content, unethical behavior, jailbreaking, and hallucination-related risks such as context relevance, groundedness, and answer relevance for retrieval-augmented generation (RAG). Trained on a unique dataset combining human annotations from diverse sources and synthetic data, Granite Guardian models address risks typically overlooked by traditional risk detection models, such as jailbreaks and RAG-specific issues. With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space. Released as open-source, Granite Guardian aims to promote responsible AI development across the community. https://github.com/ibm-granite/granite-guardian

The emergence of large language models (LLMs) enables the development of intelligent agents capable of engaging in complex and multi-turn dialogues. However, multi-agent collaboration faces critical safety challenges, such as hallucination amplification and error injection and propagation. This paper presents GUARDIAN, a unified method for detecting and mitigating multiple safety concerns in GUARDing Intelligent Agent collaboratioNs. By modeling the multi-agent collaboration process as a discrete-time temporal attributed graph, GUARDIAN explicitly captures the propagation dynamics of hallucinations and errors. The unsupervised encoder-decoder architecture incorporating an incremental training paradigm learns to reconstruct node attributes and graph structures from latent embeddings, enabling the identification of anomalous nodes and edges with unparalleled precision. Moreover, we introduce a graph abstraction mechanism based on the Information Bottleneck Theory, which compresses temporal interaction graphs while preserving essential patterns. Extensive experiments demonstrate GUARDIAN's effectiveness in safeguarding LLM multi-agent collaborations against diverse safety vulnerabilit

Current online safety technologies overly rely on parental mediation and often fail to address the unique challenges faced by youth in the Child Welfare System (CWS). These youth depend on a complex ecosystem of support, including families, caseworkers, and advocates, to safeguard their wellbeing. Within this network, Guardians ad Litem (GALs) play a unique role as court-appointed advocates tasked with ensuring the best interests of youth. Yet little is known about how GALs perceive and support youths' online safety. To address this gap, we conducted a two-part workshop with 10 GALs to explore their perspectives on online safety and collaboratively envision technology-based solutions tailored to the needs of youth in the CWS. Our findings revealed that GALs struggle to support youth with online safety challenges due to limited digital literacy, inconsistency of institutional support, lack of collaboration among stakeholders, and complexity of family dynamics. While GALs recognized the need for some oversight of youth online activities, they emphasized designing systems that support online safety beyond control or restriction by fostering stability, trust, and meaningful interaction

The current "notice and consent" paradigm is broken: consent dialogues are often manipulative, and users cannot realistically read or understand every privacy policy. While recent LLM-based tools empower users seeking active control, many with limited time or motivation prefer full automation. However, fully autonomous solutions risk hallucinations and opaque decisions, undermining trust. I propose a middle ground - a Privacy Guardian Agent that automates routine consent choices using user profiles and contextual awareness while recognizing uncertainty. It escalates unclear or high-risk cases to the user, maintaining a human-in-the-loop only when necessary. To ensure agency and transparency, the agent's reasoning on its autonomous decisions is reviewable, allowing for user recourse. For problematic cases, even with minimal consent, it alerts the user and suggests switching to an alternative site. This approach aims to reduce consent fatigue while preserving trust and meaningful user autonomy.

Model stealing attack is increasingly threatening the confidentiality of machine learning models deployed in the cloud. Recent studies reveal that adversaries can exploit data synthesis techniques to steal machine learning models even in scenarios devoid of real data, leading to data-free model stealing attacks. Existing defenses against such attacks suffer from limitations, including poor effectiveness, insufficient generalization ability, and low comprehensiveness. In response, this paper introduces a novel defense framework named Model-Guardian. Comprising two components, Data-Free Model Stealing Detector (DFMS-Detector) and Deceptive Predictions (DPreds), Model-Guardian is designed to address the shortcomings of current defenses with the help of the artifact properties of synthetic samples and gradient representations of samples. Extensive experiments on seven prevalent data-free model stealing attacks showcase the effectiveness and superior generalization ability of Model-Guardian, outperforming eleven defense methods and establishing a new state-of-the-art performance. Notably, this work pioneers the utilization of various GANs and diffusion models for generating highly reali

Mass gathering events are associated with critical safety incidents caused by insufficient crowd monitoring and inadequate emergency response coordination. Traditional surveillance systems lack intelligent analytics, resulting in delayed threat identification, poor resource deployment, and weak support for vulnerable individuals during dense public assemblies. This paper presents Drishti AI-Event Guardian, an intelligent crowd management framework using deep learning for public safety enhancement. The architecture combines multimodal data from CCTV networks and UAV platforms, processed by models on Google Vertex AI infrastructure. Core methods include real-time crowd density estimation using YOLOv8, spatiotemporal anomaly detection, and predictive crowd-flow modeling through gradient-boosted regression. Drishti also integrates four modules: (i) facial recognition for missing person identification with crowd-wide notification; (ii) medical emergency reporting with automated dispatch; (iii) a conversational AI chatbot for reports and complaints; and (iv) an intelligent guard reallocation engine that dynamically reassigns personnel in response to crowd density changes. The system is e

As Agentic AI gain mainstream adoption, the industry invests heavily in model capabilities, achieving rapid leaps in reasoning and quality. However, these systems remain largely confined to data silos, and each new integration requires custom logic that is difficult to scale. The Model Context Protocol (MCP) addresses this challenge by defining a universal, open standard for securely connecting AI-based applications (MCP clients) to data sources (MCP servers). However, the flexibility of the MCP introduces new risks, including malicious tool servers and compromised data integrity. We present MCP Guardian, a framework that strengthens MCP-based communication with authentication, rate-limiting, logging, tracing, and Web Application Firewall (WAF) scanning. Through real-world scenarios and empirical testing, we demonstrate how MCP Guardian effectively mitigates attacks and ensures robust oversight with minimal overheads. Our approach fosters secure, scalable data access for AI assistants, underscoring the importance of a defense-in-depth approach that enables safer and more transparent innovation in AI-driven environments.

Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution can exploit these mechanisms to discriminate or unjustly deny services under the guise of uncertainty. We demonstrate the practicality of this threat by introducing an uncertainty-inducing attack called Mirage, which deliberately reduces confidence in targeted input regions, thereby covertly disadvantaging specific individuals. At the same time, Mirage maintains high predictive performance across all data points. To counter this threat, we propose Confidential Guardian, a framework that analyzes calibration metrics on a reference dataset to detect artificially suppressed confidence. Additionally, it employs zero-knowledge proofs of verified inference to ensure that reported confidence scores genuinely originate from the deployed model. This prevents the provider from fabricating arbitrary model confidence values while protecting the model's proprietary details. Our results confirm that Confidential Guardian effectively prevents the misuse of cautious predictions, p

Modern GPU applications, such as machine learning (ML), can only partially utilize GPUs, leading to GPU underutilization in cloud environments. Sharing GPUs across multiple applications from different tenants can improve resource utilization and consequently cost, energy, and power efficiency. However, GPU sharing creates memory safety concerns because kernels must share a single GPU address space. Existing spatial-sharing mechanisms either lack fault isolation for memory accesses or require static partitioning, which leads to limited deployability or low utilization. In this paper, we present Guardian, a PTX-level bounds checking approach that provides memory isolation and supports dynamic GPU spatial-sharing. Guardian relies on three mechanisms: (1) It divides the common GPU address space into separate partitions for different applications. (2) It intercepts and checks all GPU related calls at the lowest level, fencing erroneous operations. (3) It instruments all GPU kernels at the PTX level -- available in closed GPU libraries -- fencing all kernel memory accesses outside application memory bounds. Guardian's approach is transparent to applications and supports real-life framewo

Modern text-to-image generative models can inadvertently reproduce copyrighted content memorized in their training data, raising serious concerns about potential copyright infringement. We introduce Guardians of Generation, a model agnostic inference time framework for dynamic copyright shielding in AI image generation. Our approach requires no retraining or modification of the generative model weights, instead integrating seamlessly with existing diffusion pipelines. It augments the generation process with an adaptive guidance mechanism comprising three components: a detection module, a prompt rewriting module, and a guidance adjustment module. The detection module monitors user prompts and intermediate generation steps to identify features indicative of copyrighted content before they manifest in the final output. If such content is detected, the prompt rewriting mechanism dynamically transforms the user's prompt by sanitizing or replacing references that could trigger copyrighted material while preserving the prompt's intended semantics. The adaptive guidance module adaptively steers the diffusion process away from flagged content by modulating the model's sampling trajectory. T

Soft boundaries, like thin hairs, are commonly observed in natural and computer-generated imagery, but they remain challenging for 3D vision due to the ambiguous mixing of foreground and background cues. This paper introduces Guardians of the Hair (HairGuard), a framework designed to recover fine-grained soft boundary details in 3D vision tasks. Specifically, we first propose a novel data curation pipeline that leverages image matting datasets for training and design a depth fixer network to automatically identify soft boundary regions. With a gated residual module, the depth fixer refines depth precisely around soft boundaries while maintaining global depth quality, allowing plug-and-play integration with state-of-the-art depth models. For view synthesis, we perform depth-based forward warping to retain high-fidelity textures, followed by a generative scene painter that fills disoccluded regions and eliminates redundant background artifacts within soft boundaries. Finally, a color fuser adaptively combines warped and inpainted results to produce novel views with consistent geometry and fine-grained details. Extensive experiments demonstrate that HairGuard achieves state-of-the-art

This paper introduces a reaction-advection-diffusion system that models interactions among three actors: a target, a partaker, and a guardian. The framework is versatile, capturing phenomena ranging from the emergence and movement of crime hotspots in urban areas to shifts in public attitudes during critical events as individuals and control units move through space. We prove local and global existence of solutions under realistic assumptions and showcase the model through two applications: protest dynamics driven by new demonstrators joining and escalating hostility in enclosed environments such as classrooms or offices. Numerical simulations highlight the resulting complex spatial patterns and temporal dynamics.

We study a reaction-advection-diffusion model of a target-offender-guardian system designed to capture interactions between urban crime and policing. Using Crandall-Rabinowitz bifurcation theory and spectral analysis, we establish rigorous conditions for both steady-state and Hopf bifurcations. These results identify critical thresholds of policing intensity at which spatially uniform equilibria lose stability, leading either to persistent heterogeneous hotspots or oscillatory crime-policing cycles. From a criminological perspective, such thresholds represent tipping points in guardian mobility: once crossed, they can lock neighborhoods into stable clusters of criminal activity or trigger recurrent waves of hotspot formation. Numerical simulations complement the theory, exhibiting stationary patterns, periodic oscillations, and chaotic dynamics. By explicitly incorporating law enforcement as a third interacting component, our framework extends classical two-equation models. It offers new tools for analyzing nonlinear interactions, bifurcations, and pattern formation in multi-agent social systems.