Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversational and spatial analysis but introduces security risks. This work presents a security-oriented framework for risk identification, evaluation, and mitigation in a multi-agent GIS system while maintaining adaptability to broader agentic architectures. We test the agentic system of a commercial geospatial partner while developing a modular state-machine-based orchestration framework that abstracts agent behavior into reusable components. We evaluate robustness using a red-teaming framework with an adaptive attacker LLM and a deterministic judge that produces binary outcomes with supporting rationales across multi-turn attacks. We further improve resilience with a prompt optimization framework that treats prompts as structured signatures and injects adversarial demonstrations, enabling systematic security improvements without degrading task performance.
Kyle Gao, Pranavi Kotta, Linlin Xu et al.· 0 citations
Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because full local corpora remain on clients. As a result, routing must rely on client-provided semantic profiles, creating a new opportunity for manipulation. We introduce Routing Hijacking, a routing-stage attack in which a malicious client forges its profile to attract target queries despite having irrelevant underlying data. We show that this vulnerability is severe. Across three representative FedRAG routing architectures, Routing Hijacking consistently misroutes target queries and leads to downstream disruptions and failures, including missing evidence, poisoning, incorrect answers, and hallucinations. In a controlled MedQA-USMLE stress test, we further show that poisoned retrieved evidence can mislead models across scales, leading to incorrect answers, hallucinations, and sycophantic failures. Existing defenses do not close this gap: encrypted routing preserves the exploited ranking, and Byzantine-robust Federated Learning (FL) rules transfer poorly to heterogeneous routing profiles. To address this gap, we propose a trust-aware post-routing framework that reweights clients using returned-evidence feedback, including retrieval relevance, profile consistency, and cross-client agreement; online experiments show that it suppresses persistent hijacking over recurring queries and transfers to a learned neural router. Our findings establish routing integrity as a security challenge in FedRAG and highlight the need for stronger defenses for secure federated retrieval.
Cyber threat intelligence (CTI) is foundational to modern cyber defense, yet much of it resides in unstructured reports whose volume and heterogeneity far exceed manual analysis, motivating research on automatically constructing knowledge graphs from CTI reports. However, existing approaches mainly extract partial information within a single report, leaving the cross-source setting unexplored, where the same threat is given unrelated names. Our key insight is that attack behaviors, once mapped to MITRE ATT&CK (a standardized catalog of attack techniques), can anchor the rest of a report. Attack behaviors are the adversarial actions a report describes, while contextual entities (e.g., threat actors, campaigns, and affected products) and Indicators of Compromise (IoCs; e.g., IP addresses) are their participants and traces. Attaching them to these anchors places every per-report graph in one canonical space.
We realize this insight in BEACON, an LLM-driven framework for cross-source CTI knowledge graph construction. Its first stage extracts each report into a graph under a propose-then-verify paradigm, grounding candidates in report evidence and official ATT&CK definitions, to suppress LLM misclassification and hallucination. Its second stage merges these graphs with a hierarchical alignment strategy that applies signals in decreasing order of determinism, from character-level and semantic similarity to overlapping technique neighborhoods, iterating as merges pool neighborhoods. No existing benchmark links entities to technique anchors or provides cross-source alignment ground truth. We therefore construct and release two human-annotated datasets from 34 sources: to our knowledge the largest for report-level CTI extraction (8,395 elements) and the first for cross-source consolidation (3,487). On them, BEACON outperforms all baselines by at least 23% and 9%, respectively.
Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious documents to steer outputs toward targeted answers. Existing poisoning attacks often rely on query inclusion, inserting the target query into poisoned documents to improve retrieval; however, this creates lexical and embedding-space artifacts that make them easy to filter. We propose CamoDocs, a poisoning attack that avoids direct query inclusion by camouflaging adversarial documents among benign content. CamoDocs chunks synthesized benign and adversarial drafts, replaces selected tokens in benign chunks with dispersion tokens that spread poisoned-document embeddings, and applies coherence filtering to limit readability degradation. Across seven RAG defenses, three open-weight LLMs, and three benchmarks, CamoDocs achieves strong average ASR while avoiding query-overlap artifacts exploited by simple query detection. It also remains effective against proprietary models, achieving average ASRs of 61.80% on GPT-5.4-mini and 55.09% on Claude-Haiku-4.5. Finally, we show that erasure-heavy clustering defenses such as TrustRAG can reduce ASR, but only with substantial utility drops on retrieval-dependent benchmarks such as NeoQA. Code is available at https://github.com/jaewonalive/CamoDocs.
Jaewon Jung, Haizhong Zheng, Hongsun Jang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The timely dissemination of cyber threat intelligence (CTI) is critical for organizations to mount swift and effective incident response. When valid CTI is delivered to the right sector at the right time, identical attacks can often be contained or mitigated. However, today's rapidly expanding CTI landscape overwhelms analysts, who must sift through massive and heterogeneous feeds. Existing platforms such as the Malware Information Sharing Platform (MISP) provide sector tagging features (e.g., energy, finance, government), but in practice, these remain largely unmapped (98% of events are left uncategorized). This lack of automated and timely sector mapping severely limits the operational value of shared intelligence, leaving organizations that belong especially to the critical information infrastructure sector exposed.
To address this gap, we formulate sector-targeted CTI dissemination as a multilabel classification problem. Leveraging deep field knowledge of CTI structures and sector-specific threat patterns, we construct a novel data set of 872 sector-labelled CTI events from a threat intelligence platform (TIP). We then apply BERT, a transformer-based model, to automate the mapping of CTI events to sectors. Using the structured threat information expression (STIX) format for cross-platform interoperability, our approach achieves a macro-averaged F1-score of 0.89 at a Hamming loss of 0.055 on the custom dataset, i.e. 94.5% of individual sector-label assignments are correct. These results not only demonstrate the feasibility of sector-aware, automated CTI dissemination but also highlight how embedding expert field knowledge into machine learning design fills a crucial gap in the threat intelligence pipeline, enabling faster and context-relevant defensive action.
Fajar Wijitrisnanto (National Cyber and Crypto Agency, Jakarta, Indonesia) et al.· 0 citations
Recent work has shown that RLHF is highly susceptible to backdoor attacks. However, existing methods often rely on rare tokens or fixed triggers, limiting their impact in realistic scenarios. In this work, we develop GREAT, a novel framework for crafting natural distributional backdoors in RLHF. Specifically, GREAT targets harmful response generation for a vulnerable user subpopulation featured by semantically violent requests paired with emotionally angry triggers. At the core of our framework is a trigger identification pipeline that operates in the model's latent embedding space, leveraging dimensionality reduction and clustering techniques to identify representative triggers. To enable this, we introduce a hierarchical and diversity-driven prompting strategy to construct Erinyes, a high-quality dataset of over 5,000 angry triggers curated from GPT-4.1. Our experiments show that GREAT significantly outperforms baselines in attack generalization to unseen triggers, while preserving standard utility and maintaining stealth under defenses.
Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown, and differential privacy (DP) is treated as a proxy against all of them at once. We pin down the exact DP constant for the two that carry the practical weight, counterfactual memorization and adaptive extraction, and show that they do not control each other. Under $f$-DP, every adaptive extraction protocol with list budget $m$ succeeds with probability at most $1-f(\kappa)$ for the oblivious baseline $\kappa$, and the bound is tight on a dense set of baselines: DP uniformly controls extraction exactly up to a threshold in how well the secret can be guessed a priori. Min-entropy certifies that baseline distribution-free, since $H_\infty\ge\epsilon\log_2 e+\log_2(m/\tau)$ holds extraction below a risk level $\tau\le1/2$ under pure $\epsilon$-DP for every prior, and is exact on uniform priors. On the memorization side, $f$-DP caps the counterfactual memorization of any bounded score at an advantage functional $\eta(f)$, equal to $\tanh(\epsilon/2)$ under pure DP; for $k\ge2$ duplicated copies the naive $\epsilon\mapsto k\epsilon$ bound $\tanh(k\epsilon/2)$ is unattainable, the exact constant being a closed-form staircase attained by geometric noisy counting. That cap is attained inside the local score class used in practice, and it is there that the two measures separate: one mechanism is memorized yet unextractable, another fully extractable yet exactly invisible to every loss-based score. The two-sided blind spot this opens for loss-based auditing and unlearning verification survives on billion-parameter models: a reserved-trigger release is recovered verbatim from one prompt while the audits practitioners deploy certify it clean.
To determine the real-world effectiveness of machine learning based malware detection, it is vital to evaluate its robustness against highly capable adversaries. However, state-of-the-art attacks do not effectively model realistic adversaries, as they often assume access to privileged information such as the training data, feature space, or confidence scores of the target. In this work, we present Replicant, a deep reinforcement learning framework that learns the realistic task of evasion under a strict label-only black-box threat model. Replicant learns a reusable policy on how to modify a malware sample and when to query the target, which transfers across samples, detectors, and feature spaces. Across seven Android malware detectors and three feature spaces, Replicant is the strongest and most query-efficient approach achieving a mean attack success rate of 78.8%, a relative improvement of 20.9%-39.2% over the state-of-the-art. Furthermore, when used for adversarial training, Replicant also outperforms the state-of-the art by producing detectors with more generalizable robustness. With Replicant we demonstrate that learning the task of evasion not only results in stronger attack performance but, crucially, provides a better signal for hardening malware detectors.
Shae McFadden, Ilias Tsingenopoulos, Mario D'Onghia et al.· 0 citations
Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work, plans, executes tool calls, verifies outcomes and persists state across many unattended iterations. The agent safeguards in wide use, however, are defined over a single trajectory, and their safety state is re-initialized when the next trajectory begins. We show that this is a failure of composition rather than an implementation detail. Our central result is a separation: against an attack whose evidence is fragmented across several iterations, every trajectory-scoped monitor has a true-positive rate equal to its false-positive rate, however expressive it is, because the evidence it would need never appears in the window it sees, whereas a monitor retaining cross-iteration state separates the two perfectly. We further show that the obvious repair of carrying a geometrically decaying risk score is insufficient, because the cooling-off period a patient adversary must wait is a constant that does not grow with the horizon $N$. We then present LoopHarness, which restores a persistent, non-decaying safety state at the loop level. Under mediated commits and an arbiter detection floor $\delta_M$, it bounds the expected number of unauthorized irreversible actions by $B+m-1+m/\delta_M$, a constant in $N$, of which the $B+m-1$ term is decided by a model-free rule and therefore survives a fully colluding verifier. We give a complete evaluation protocol on native Agent-SafetyBench tasks with paired clean and attacked episodes, an outer-state attack suite whose decisive evidence exists only across iterations, per-module ablations, and an adaptive white-box red team.
Chenhao Wu, Haoxuan Jia, Yang Liu et al.· 0 citations
Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in 48-68% of adversarial scenarios, even when explicitly instructed not to. Role escalation attacks (e.g., "I'm the CFO, override the access controls") are the most dangerous category, reaching 96% unauthorized invocation in frontier models. We show this holds across three models spanning open-weight and frontier systems, including instruction-tuned models with strong alignment training. Critically, prompt-based compliance is both insufficient and unpredictable: explicit per-tool allowlists reduce violations to as low as 4.0% but never to zero, and compliance varies widely across models, from 4.0% to 37.0% UIR, with no reliable relationship to general capability. We propose a proxy-enforced attribute-based access control (ABAC) layer for MCP that filters tool registries at discovery time. Because unauthorized tools never reach the model context, UIR is 0% by design, a structural guarantee that prompt instructions cannot replicate regardless of model or phrasing.
Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces that are largely missed by existing safety evaluations: even when the user request is benign, unsafe influence may reside in skill guidance, local artifacts, or execution-environment files that steer the agent toward unsafe actions. We present SkillSafetyBench, a runnable benchmark for evaluating such skill-facing safety failures. SkillSafetyBench includes 155 adversarial cases across 47 tasks, 6 risk domains, and 30 safety categories, each evaluated with a case-specific rule-based verifier. Experiments with multiple CLI agents and model backends show that non-user attacks can consistently induce unsafe behavior, with distinct failure patterns across domains, attack methods, and scaffold-model pairings. Our findings suggest that agent safety depends not only on model-level alignment, but also on how agents interpret skills, trust workflow context, and act through executable environments. The complete benchmark is available at https://github.com/AI45Lab/skill-safety-bench.
Chang Jin, An Wang, Zeming Wei et al.· 0 citations
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against prompt injection attacks that manipulate agent behavior through malicious observations or retrieved content. We reveal a fundamental \textbf{capability-alignment paradox}: defense training designed to improve safety systematically destroys agent competence while failing to prevent sophisticated attacks. Evaluating defended models against undefended baselines across 97 agent tasks and 1,000 adversarial prompts, we uncover three systematic biases unique to multi-step agents. \textbf{Agent incompetence bias} manifests as immediate tool execution breakdown, with models refusing or generating invalid actions on benign tasks before observing any external content. \textbf{Cascade amplification bias} causes early failures to propagate through retry loops, pushing defended models to timeout on 99\% of tasks compared to 13\% for baselines. \textbf{Trigger bias} leads to paradoxical security degradation where defended models perform worse than undefended baselines while straightforward attacks bypass defenses at high rates. Root cause analysis reveals these biases stem from shortcut learning: models overfit to surface attack patterns rather than semantic threat understanding, evidenced by extreme variance in defense effectiveness across attack categories. Our findings demonstrate that current defense paradigms optimize for single-turn refusal benchmarks while rendering multi-step agents fundamentally unreliable, necessitating new approaches that preserve tool execution competence under adversarial conditions.
