Search arXiv⌕ Search

arXiv subjects

Hamed Haddadi

Publications and source records attributed to Hamed Haddadi.

At least 19 recordsLinked to original sources
arXiv2026

Airlock: Bounding the Multi-Agent Blast Radius via Selective Online Containment

When multi-agent systems act on the external world, a single agent's faulty output can spread across tasks before detection, creating a system-wide blast radius. Single-agent guardrails are confined to individual harnesses, while existing multi-agent controls either cancel only the faulty source and miss downstream consumers or halt and roll back the entire workflow at the cost of healthy work. We present Airlock, a multi-agent runtime and guardrail for selective post-alert fault containment. Its tree-structured runtime, EdgeCitadel, narrows permissions vertically from parent to child agents to establish node boundaries and control switches. Meanwhile, an append-only provenance DAG records cross-agent data consumption horizontally. Upon an alert, Airlock traces forward on this DAG to isolate tainted executions and pending actions, and backward to narrow root causes. At the site switches, a default full quarantine tier freezes affected branches without a solver, while an assured optimized cut tier uses fence-then-prune to enforce a deadline-aware minimum cut minimizing collateral disruption. Across 1,832 testbed runs, 161 physical smart-home LLM runs, and 24,266 simulation records, Airlock blocks all post-alert faulty actuations on our main testbed and smart-home grids with zero post-convergence leaks. Whereas native controls in A2A and LangGraph either contain at most 33.3% of faults or retain at most 16% of work without redo, Airlock retains +68 pp to +96 pp more healthy work, and its optimized cut retains +46 pp more than full quarantine under dense spread. These results show that co-designing runtime authority boundaries with online provenance enables surgical fault containment without sacrificing healthy work (code: https://github.com/EdgeCitadelTeam/EdgeCitadel).

cs.MA↗
arXiv2026

Can We Rely on Language Models to Orchestrate Services across the Edge-Cloud Continuum?

Service orchestration across the edge--cloud continuum increasingly uses language models (LMs) to translate intents and operational evidence into scheduling, configuration, diagnosis, and remediation decisions. Yet, useful model outputs do not by themselves establish dependable orchestration: reliability also depends on where the LM enters the decision process, what authority it is granted, how actions are constrained, and what system-level evidence supports the claimed effect. Existing surveys provide limited synthesis of the links between continuum-specific orchestration decisions, LM responsibility, operational authority, assurance controls, and supporting empirical evidence. We systematically review 39 primary studies and develop a five-dimensional analytical framework for connecting system context, orchestration decisions, LM agency, operational safeguards, and evaluation evidence. The synthesis reveals predominantly hybrid designs in which LMs support interpretation, candidate generation, and mitigation planning, while downstream components commonly retain feasibility enforcement and execution authority. Bounded closed-loop remediation is emerging, but continuum-specific constraints remain unevenly represented in decision formulations, and production-scale evidence across heterogeneous edge--cloud environments remains limited. These findings suggest that reliance on LM-enabled orchestration depends on aligning decision constraints, operational authority, safeguards, and evaluation evidence with the claimed system effect.

cs.DC↗
arXiv2026

When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels

Approximate unlearning answers a deletion request on a knowledge-graph embedding by editing entity embeddings instead of retraining from scratch. These embeddings keep being updated as new facts arrive. Under this ordinary continued training, forgotten facts recover more than in the exact-unlearning baseline, a model retrained without them and given the same continued training. We trace this relearning to entity embeddings shared by forgotten and new facts. To our knowledge, this is the first study of relearning in knowledge-graph embeddings. Relearning-robust methods developed for deep networks do not account for the graph structure underlying this recovery. We propose Kernel-Anticipated Unlearning (KAU), which uses the tangent kernel to model how continued training changes forgotten facts' scores through these shared parameters. KAU expresses this first-order response in closed form and differentiates through it inside the forgetting loss. The objective steers edits toward directions that continued training reverses less. We compare KAU with state-of-the-art knowledge-graph unlearners and relearning-robust methods under identical continued training, measuring leakage beyond the exact-unlearning baseline. Across three backbones, KAU reduces the strongest knowledge-graph unlearner's leakage by 46-63% on FB15k-237 and 50-82% on CoDEx-L, at higher retained utility.

cs.LG↗
arXiv2026

Sharing is caring: Attestable and Trusted Workflows out of Distrustful Components

Trusted Execution Environments (TEEs) protect private memory and attest initial code and configuration, but neither constrain nor attest shared channels between TEEs or with the untrusted host. Confidentiality thus depends on the functional correctness of all in-TEE code accessing these channels: a single misuse can leak data and compromise a pipeline. This assumption is increasingly untenable for agentic applications that generate code at runtime and cloud pipelines of mutually distrustful components. We present MICA, a confidential-computing firmware extension that decouples confidentiality from trust in in-TEE code. MICA lets tenants define, restrict, and attest channel constraints between TEEs and with the untrusted host, including transitive constraints spanning a pipeline. It extends attestation to groups of communicating TEEs, letting external parties verify the confidentiality properties induced by these constraints across a pipeline. We implement MICA on Arm CCA by extending the Realm Management Monitor with a small policy language, requiring no hardware changes and minor QEMU and KVM changes. Our evaluation demonstrates support for confidential agentic applications and pipeline computations without trusting the functional correctness of in-TEE code. MICA increases the TCB by 7% and incurs infrequent setup costs: 2-4% boot-time overhead, approximately 1.5 s for policy upload, and 246-598 ms for group attestation. Once established, Realm communication is direct, uses protected memory, and requires no MICA intervention or software encryption, yielding up to 14.5 times lower cross-TEE message latency than encrypted communication over untrusted memory.

cs.CR↗
arXiv2026

Can Generative Retrievers Learn Semantic IDs Without Forgetting How to Speak?

Generative retrieval (GR) enables end-to-end retrieval by generating document semantic identifiers (SIDs). However, retrieval-only fine-tuning can over-specialize pretrained language models to SID prediction, substantially distorting their natural-language distribution and limiting their suitability for interactive systems that must both retrieve documents and generate natural-language responses. We introduce SpeakGR, a dual-objective framework that learns SIDs while preserving language generation. It combines supervised SID learning with speak-preserving regularization: an on-policy distillation objective that aligns the current model with a frozen copy of the original model on student-generated prefixes using forward KL over the original text vocabulary. We further propose Adaptive SpeakGR, which dynamically adjusts the preservation strength based on observed language drift. Compared with SFT-only, SpeakGR reduces WikiText-2 forward KL by 81.3-93.8% on MS MARCO and 81.2-85.2% on Natural Questions (NQ) while retaining effective retrieval across three different LLMs. Adaptive SpeakGR further improves retrieval over SpeakGR in most settings while maintaining substantially lower language drift than SFT-only.

cs.IR↗
arXiv2026

SimVerity: When Does Simulated Agent Success Survive Physical Deployment?

Simulated evaluation is widely used to benchmark AI agents, yet how much evidence a simulated pass provides about physical deployment has not been systematically quantified. We present SimVerity, a verdict-transfer assurance framework: it replays matched scenarios on target smart home deployments and cross-validates agent execution against independently qualified physical witnesses. Our evaluation highlights that deployment success is a real-world process, not a static property in simulation: completion, reported state, observable effect, and settled outcome diverged within the same execution. Although an advanced simulator cleared all 240 light trials, a camera caught 42 sub-second failures invisible to settled-state checks. False clearance was predictable: a risk profile learned from measured trials and locked before evaluation predicted failures on a path it never physically measured, beating a property-blind baseline in all eleven held-out sessions across two cohorts. Agent auditability was also measurable: switching one agent loop's model-client/serving configuration raised its scenario-matching share from 52-88% to 100%. Finally, a second qualified simulator added no independent cross-check: it never disagreed on any overlapping case, and only physical measurement exposed their shared blind spots. SimVerity turns verdict transfer into an explicit decision: clear, abstain, or escalate before deployment.

cs.AI↗
arXiv2026

Auto-Policy, not Auto-Skill: Compiled Agent Skills for the Physical World

Self-evolving Skill harnesses (AutoSkills, Hermes Agent) generate more advisory orchestration automatically; their reported gains are efficiency, not safety. This misses the actual gap: a Skill describes how an agent should behave; a Policy decides which behavior is allowed to become an action. Today's format covers the first with markdown and scripts; the second is left to the model. Generating more Skills scales the gap, not the safety, especially when a wrong invocation can unlock a door or move money. Two adjacent attacks are documented: malicious skills compromising cloud software, and jailbroken LLM-controlled robots causing physical harm. Their intersection, malicious agent skills causing physical harm, follows directly but has not been reported. We name this class Borrowed Authority: Skills format gives the receiving agent no typed way to reject an inter-agent permission claim, so a malicious or misused Skill can drive actuation by attaching one. We propose Edge Skillguard, a typed authority layer that lives inside the Skill artifact rather than between tools as workflow engines do, with guards over world state and sensor evidence. On a live edge control-plane testbed, the guards reject 60/60 borrowed-authority requests across five attack variants without blocking benign requests, and the result holds at 5x scale and across hosts over a Tailscale mesh. These results suggest that high-risk Skills should co-package typed invocation policy with procedural knowledge, so that physical actions depend on machine-checkable evidence rather than peer-agent claims.

cs.AI↗
arXiv2026

Safe Skill Retirement for Physical Agents

Agent skills bundle procedural guidance with execution conditions governing authority, user consent, and live environment state. When model capabilities advance, maintainers prune instructions that appear redundant on authorized benchmark tasks. However, authorized maintenance tests can leave dormant safety conditions untested. This mismatch creates an unmeasured support gap over physical and privacy-sensitive effects. We introduce matched authority counterfactuals that hold the requested action, tool parameters, and intended effect fixed while systematically varying a single governing predicate. We formalize this evaluation via a two-gate retirement certificate requiring a candidate reduction to preserve authorized utility within a declared margin while producing zero unauthorized protected effects. In controlled experiments spanning four frontier and local model configurations across twelve skill bundles (2,592 evaluation cells), task-certified reductions remove over 94% of skill clauses and preserve authorized completion, yet produce unauthorized protected effects in every bundle. Boundary enforcement eliminates protected effects on the declared audit but fails the utility gate for one configuration. One bounded combined protocol passes both gates across all four configurations, with zero utility headroom. An end-to-end check on one read-only Home Assistant camera chain verifies proposal, decision, and effect measurements on a real device. These results demonstrate that while task benchmarks can justify retiring procedural guidance, retirement decisions require explicitly auditing the authority contracts governing physical actions.

cs.AI↗
arXiv2026

CERTIoT-6G: Continuous Cybersecurity Certification for IoT Devices in 5G/6G Networks

The massive adoption of Internet of Things (IoT) devices across critical domains such as healthcare, smart cities, industrial automation, and critical infrastructure introduces significant cybersecurity and regulatory challenges. Current and forthcoming European regulations, including the Cyber Resilience Act (CRA) and the NIS2 Directive, require manufacturers, operators, and other organizations to ensure secure-by-design devices, continuous vulnerability management, and resilient operation throughout the device lifecycle. Traditional certification mechanisms remain static, manual, and difficult to scale across heterogeneous IoT ecosystems. This paper presents CERTIoT-6G, a Security-as-a-Service (SECaaS) framework that enables automated cybersecurity certification and continuous compliance monitoring of IoT devices operating in 5G and future 6G networks. The framework integrates automated compliance analysis, real-time traffic monitoring, and adversarial testing capabilities. We validate the CERTIoT-6G framework on different IoT device categories operating in an advanced 5G testbed. Evaluation results reveal critical compliance gaps, particularly in traffic encryption and availability under unstable conditions, and demonstrate that the framework produces actionable verdicts mapped to regulatory requirements across heterogeneous device types. Furthermore, we show that the monitoring pipeline has a negligible impact on live 5G traffic.

cs.NI↗
arXiv2026

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone model inference. Agents accumulate sensitive context, hold credentials, and operate across pipelines no single party fully controls, enabling prompt injection, context exfiltration, credential theft, and inter-agent message poisoning. Current defenses operate entirely within the software stack and can be silently bypassed by a sufficiently privileged adversary such as a compromised cloud operator. Confidential computing (CC) offers a hardware-rooted alternative: Trusted Execution Environments (TEEs) isolate agent code and data from privileged system software, while remote attestation enables verifiable trust across distributed deployments. This survey synthesizes the design space in four parts: (i) a unified taxonomy of six TEE platforms (Intel SGX, Intel TDX, AMD SEV-SNP, ARM TrustZone, ARM CCA, and NVIDIA H100 CC) covering deployment roles and performance tradeoffs; (ii) an agent-centric threat model spanning perception, planning, memory, action, and coordination layers mapped to nine security goals; (iii) a comparative survey of CC-based defenses distinguishing findings that transfer from single-call inference versus what requires new agentic designs; and (iv) six open challenges including compound attestation for multi-hop agent chains and GPU-TEE performance at LLM scale. While several hardware trust primitives appear mature enough for targeted deployments, no broadly established end-to-end framework yet binds them into a coherent security substrate for production agentic AI.

cs.CR↗
arXiv2026

CAEC: Confidential, Attestable, and Efficient Inter-CVM Communication with Arm CCA

Confidential Virtual Machines (CVMs) are increasingly adopted to protect sensitive workloads from privileged adversaries such as the hypervisor. While they provide strong isolation guarantees, existing CVM architectures lack first-class mechanisms for inter-CVM data sharing due to their disjoint memory model, making inter-CVM data exchange a performance bottleneck in compartmentalized or collaborative multi-CVM systems. Under this model, a CVM's accessible memory is either shared with the hypervisor or protected from both the hypervisor and all other CVMs. This design simplifies reasoning about memory ownership; however, it fundamentally precludes plaintext data sharing between CVMs because all inter-CVM communication must pass through hypervisor-accessible memory, requiring costly encryption and decryption to preserve confidentiality and integrity. In this paper, we introduce CAEC, a system that enables protected memory sharing between CVMs. CAEC builds on Arm Confidential Compute Architecture (CCA) and extends its firmware to support Confidential Shared Memory (CSM), a memory region securely shared between multiple CVMs while remaining inaccessible to the hypervisor and all non-participating CVMs. CAEC's design is fully compatible with CCA hardware and introduces only a modest increase (6%) in CCA firmware code size. CAEC delivers substantial performance benefits across a range of workloads. For instance, inter-CVM communication over CAEC achieves up to 209x reduction in CPU cycles compared to encryption-based mechanisms over hypervisor-accessible shared memory. By combining high performance, strong isolation guarantees, and attestable sharing semantics, CAEC provides a practical and scalable foundation for the next generation of trusted multi-CVM services across both edge and cloud environments.

cs.CR↗
arXiv2026

AgenTEE: Confidential LLM Agent Execution on Edge Devices

Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their tight integration with non-deterministic models and third-party services. While current deployments primarily rely on cloud-hosted services, emerging designs increasingly execute agents directly on edge devices to reduce latency and enhance user privacy. However, securely hosting such complex agent pipelines on edge devices remains challenging. These deployments must protect proprietary assets (e.g., system prompts and model weights) and sensitive runtime state on heterogeneous platforms that are vulnerable to software attacks and potentially controlled by malicious users. To address these challenges, we present AgenTEE, a system for deploying confidential agent pipelines on edge devices. AgenTEE places the agent runtime, inference engine, and third-party applications into independently attested confidential virtual machines (cVMs) and mediates their interaction through explicit, verifiable communication channels. Built on Arm Confidential Compute Architecture (CCA), a recent extension to Arm platforms, AgenTEE enforces strong system-level isolation of sensitive assets and runtime state. Our evaluation shows that such multi-cVMs system is practical, achieving near-native performance with less than 5.15% runtime overhead compared to commodity OS multi-process deployments.

cs.CR↗
arXiv2026

AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices

Autonomous agents powered by large language models (LLMs) are increasingly used to automate complex, multi-step tasks such as coding or web-based question answering. While remote, cloud-based agents offer scalability and ease of deployment, they raise privacy concerns, depend on network connectivity, and incur recurring API costs. Deploying agents locally on user devices mitigates these issues by preserving data privacy and eliminating usage-based fees. However, agentic workflows are far more resource-intensive than typical LLM interactions. Iterative reasoning, tool use, and failure retries substantially increase token consumption, often expending significant compute without successfully completing tasks. In this work, we investigate the time, token, and energy overhead of locally deployed LLM-based agents on consumer hardware. Our measurements show that agentic execution increases GPU power draw, temperature, and battery drain compared to single-inference workloads. To address this inefficiency, we introduce AgentStop, a lightweight efficiency supervisor that predicts and preemptively terminates trajectories unlikely to succeed. Leveraging low-cost execution signals, such as token-level log probabilities, AgentStop can reduce wasted energy by 15-20% with minimal impact on task performance (<5% utility drop) for challenging web-based question answering and coding benchmarks. These findings position predictive early termination as a practical mechanism for enabling sustainable, privacy-preserving LLM agents on user devices. Our project code and data are available at https://github.com/brave-experiments/AgentStop.

cs.LG↗
arXiv2026

HearthNet: Edge Multi-Agent Orchestration for Smart Homes

Smart-home users increasingly want to control their homes in natural language rather than assemble rules, dashboards, and API integrations by hand. At the same time, real deployments are brittle: devices fail, integrations break, and recoveries often require manual intervention. Existing agent toolkits are effective for session-scoped delegation, but smart-home control operates under a different scenario: it is persistent, event-driven, failure-prone, and tied to physical devices with no shared context window. We present HearthNet, an edge multi-agent orchestration system for smart homes. HearthNet deploys a small set of persistent, role-specialized LLM agents at the home hub, where they coordinate through MQTT, Git-backed shared state, and root-issued actuation leases to govern heterogeneous devices through thin adapters. This design externalizes context, preserves execution history, and separates planning, verification, authorization, and actuation across explicit boundaries. Our current prototype runs on commodity edge hardware and Android devices; it keeps orchestration, state management, and device control on-premise while using hosted LLM APIs for inference. We demonstrate the system through three live scenarios: intent-driven multi-agent coordination from ambiguous natural language, conflict resolution with timeline-based tracing, and rejection of stale or unauthorized commands before device actuation.

cs.DC↗
arXiv2026

Systems-Level Attack Surface of Edge Agent Deployments on IoT

Edge deployment of LLM agents on IoT hardware introduces attack surfaces absent from cloud-hosted orchestration. We present an empirical security analysis of three architectures (cloud-hosted, edge-local swarm, and hybrid) using a multi-device home-automation testbed with local MQTT messaging and an Android smartphone as an edge inference node. We identify five systems-level attack surfaces, including two emergent failures observed during live testbed operation: coordination-state divergence and induced trust erosion. We frame core security properties as measurable systems metrics: data egress volume, failover window exposure, sovereignty boundary integrity, and provenance chain completeness. Our measurements show that edge-local deployments eliminate routine cloud data exposure but silently degrade sovereignty when fallback mechanisms trigger, with boundary crossings invisible at the application layer. Provenance chains remain complete under cooperative operation yet are trivially bypassed without cryptographic enforcement. Failover windows create transient blind spots exploitable for unauthorised actuation. These results demonstrate that deployment architecture, not just model or prompt design, is a primary determinant of security risk in agent-controlled IoT systems.

cs.CR↗
arXiv2026

Towards Real-Time ECG and EMG Modeling on $μ$NPUs

The miniaturisation of neural processing units (NPUs) and other low-power accelerators has enabled their integration into microcontroller-scale wearable hardware, supporting near-real-time, offline, and privacy-preserving inference. Yet physiological signal analysis has remained infeasible on such hardware; recent Transformer-based models show state-of-the-art performance but are prohibitively large for resource- and power-constrained hardware and incompatible with $μ$NPUs due to their dynamic attention operations. We introduce PhysioLite, a lightweight, NPU-compatible model architecture and training framework for ECG/EMG signal analysis. Using learnable wavelet filter banks, CPU-offloaded positional encoding, and hardware-aware layer design, PhysioLite reaches performance comparable to state-of-the-art Transformer-based foundation models on ECG and EMG benchmarks, while being <10% of the size ($\sim$370KB with 8-bit quantization). We also profile its component-wise latency and resource consumption on both the MAX78000 and HX6538 WE2 $μ$NPUs, demonstrating its viability for signal analysis on constrained, battery-powered hardware. We release our model(s) and training framework at: https://github.com/j0shmillar/physiolite.

cs.LG↗
arXiv2026

How Adversarial Environments Mislead Agentic AI?

Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack surface. Current evaluations benchmark capability in benign settings, asking "can the agent use tools correctly" but never "what if the tools lie". We identify this Trust Gap: agents are evaluated for performance, not for skepticism. We formalize this vulnerability as Adversarial Environmental Injection (AEI), a threat model where adversaries compromise tool outputs to deceive agents. AEI constitutes environmental deception: constructing a "fake world" of poisoned search results and fabricated reference networks around unsuspecting agents. We operationalize this via POTEMKIN, a Model Context Protocol (MCP)-compatible harness for plug-and-play robustness testing. We identify two orthogonal attack surfaces: The Illusion (breadth attacks) poison retrieval to induce epistemic drift toward false beliefs, while The Maze (depth attacks) exploit structural traps to cause policy collapse into infinite loops. Across 11,000+ runs on five frontier agents, we find a stark robustness gap: resistance to one attack often increases vulnerability to the other, demonstrating that epistemic and navigational robustness are distinct capabilities.

cs.AI↗
arXiv2026

Poster: EdgeCitadel -- Hybrid NATS-MQTT Orchestration for Edge Multi-Agent Systems

Edge-resident AI agents increasingly span home servers, IoT hubs, laptops, and phones, yet their coordination stacks still assume cloud-style transports or a central relay. We present EdgeCitadel, an edge multi-agent orchestration platform built around a single NATS 2.10 server with the built-in MQTT adapter. The design combines MQTT connectivity for heterogeneous agents, JetStream-backed persistence and replay for backend services, direct peer delegation over a shared subject namespace, and a passive aggregator that visualizes and stores traffic without sitting on the delivery path. Our poster highlights the migration from MQTT relay prototypes (common in IoT communication) to the current hybrid architecture and demonstrates a working cross-device testbed spanning ARM64, x64, and Android clients.

cs.DC↗