Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we map out the trust boundaries and security risks of agentic LLM-based systems. We develop a comprehensive taxonomy of attacks spanning prompt-level injections, knowledge-base poisoning, tool/plug-in exploits, and multi-agent emergent threats. Through a detailed literature review, we synthesize evidence from 2023-2025, including more than 20 peer-reviewed and archival studies, industry reports, and standards. We find that agentic systems introduce new vectors for indirect prompt injection, code execution exploits, RAG index poisoning, and cross-agent manipulation that go beyond traditional AI threats. We define attacker models and threat scenarios, and propose metrics (e.g., Unsafe Action Rate, Privilege Escalation Distance) to evaluate security posture. Our survey examines defenses such as input sanitization, retrieval filters, sandboxes, access control, and "AI guardrails," assessing their effectiveness and pointing out the areas where protection is still lacking. To assist practitioners, we outline defensive controls and provide a phased security checklist for deploying agentic AI (covering design-time hardening, runtime monitoring, and incident response). Finally, we outline open research challenges in secure autonomous AI (robust tool APIs, verifiable agent behavior, supply-chain safeguards) and discuss ethical and responsible disclosure practices. We systematize recent findings to help researchers and engineers understand and mitigate security risks in agentic AI.

Gradient inversion attacks reveal that private training text can be reconstructed from shared gradients, posing a privacy risk to large language models (LLMs). While prior methods perform well in small-batch settings, scaling to larger batch sizes and longer sequences remains challenging due to severe signal mixing, high computational cost, and degraded fidelity. We present SOMP (Subspace-Guided Orthogonal Matching Pursuit), a scalable gradient inversion framework that casts text recovery from aggregated gradients as a sparse signal recovery problem. Our key insight is that aggregated transformer gradients retain exploitable head-wise geometric structure together with sample-level sparsity. SOMP leverages these properties to progressively narrow the search space and disentangle mixed signals without exhaustive search. Experiments across multiple LLM families, model scales, and five languages show that SOMP consistently outperforms prior methods in the aggregated-gradient regime.For long sequences at batch size B=16, SOMP achieves substantially higher reconstruction fidelity than strong baselines, while remaining computationally competitive. Even under extreme aggregation (up to B=128), SOMP still recovers meaningful text, suggesting that privacy leakage can persist in regimes where prior attacks become much less effective.

Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a competitive alternative, yet their memorization behavior remains largely unexplored due to fundamental differences in generation dynamics. To address this gap, we present a systematic theoretical and empirical characterization of memorization in DLMs. We propose a generalized probabilistic extraction framework that unifies prefix-conditioned decoding and diffusion-based generation under arbitrary masking patterns and stochastic sampling trajectories. Theorem 4.3 establishes a monotonic relationship between sampling resolution and memorization: increasing resolution strictly increases the probability of exact training data extraction, implying that autoregressive decoding corresponds to a limiting case of diffusion-based generation by setting the sampling resolution maximal. Extensive experiments across model scales and sampling strategies validate our theoretical predictions. Under aligned prefix-conditioned evaluations, we further demonstrate that DLMs exhibit substantially lower memorization-based leakage of personally identifiable information (PII) compared to ARMs.

Constrained Reinforcement Learning (CRL) aims to optimize decision-making policies under constraint conditions, making it highly applicable to safety-critical domains such as autonomous driving, robotics, and power grid management. However, existing robust CRL approaches predominantly focus on single-step perturbations and temporally independent adversarial models, lacking explicit modeling of robustness against temporally coupled perturbations. To tackle these challenges, we propose TCRL, a novel temporal-coupled adversarial training framework for robust constrained reinforcement learning (TCRL) in worst-case scenarios. First, TCRL introduces a worst-case-perceived cost constraint function that estimates safety costs under temporally coupled perturbations without the need to explicitly model adversarial attackers. Second, TCRL establishes a dual-constraint defense mechanism on the reward to counter temporally coupled adversaries while maintaining reward unpredictability. Experimental results demonstrate that TCRL consistently outperforms existing methods in terms of robustness against temporally coupled perturbation attacks across a variety of CRL tasks.

Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image embeddings. Surprisingly, we show that semantic leakage does not require exact reconstruction of the original image. Preserving local semantic neighborhoods under embedding alignment is sufficient to expose the intrinsic vulnerability of image embeddings. Crucially, this preserved neighborhood structure allows semantic information to propagate through a sequence of lossy mappings. Based on this conjecture, we propose Semantic Leakage from Image Embeddings (SLImE), a lightweight inference framework that reveals semantic information from standalone compressed image embeddings, incorporating a locally trained semantic retriever with off-the-shelf models, without training task-specific decoders. We thoroughly validate each step of the framework empirically, from aligned embeddings to retrieved tags, symbolic representations, and grammatical and coherent descriptions. We evaluate SLImE across a range of open and closed embedding models, including GEMINI, COHERE, NOMIC, and CLIP, and demonstrate consistent recovery of semantic information across diverse inference tasks. Our results reveal a fundamental vulnerability in image embeddings, whereby the preservation of semantic neighborhoods under alignment enables semantic leakage, highlighting challenges for privacy preservation.1

Large Language Models (LLMs) have been reported to "leak" Personally Identifiable Information (PII), with successful PII reconstruction often interpreted as evidence of memorization. We propose a principled revision of memorization evaluation for LLMs, arguing that PII leakage should be evaluated under low lexical cue conditions, where target PII cannot be reconstructed through prompt-induced generalization or pattern completion. We formalize Cue-Resistant Memorization (CRM) as a cue-controlled evaluation framework and a necessary condition for valid memorization evaluation, explicitly conditioning on prompt-target overlap cues. Using CRM, we conduct a large-scale multilingual re-evaluation of PII leakage across 32 languages and multiple memorization paradigms. Revisiting reconstruction-based settings, including verbatim prefix-suffix completion and associative reconstruction, we find that their apparent effectiveness is driven primarily by direct surface-form cues rather than by true memorization. When such cues are controlled for, reconstruction success diminishes substantially. We further examine cue-free generation and membership inference, both of which exhibit extremely low true positive rates. Overall, our results suggest that previously reported PII leakage is better explained by cue-driven behavior than by genuine memorization, highlighting the importance of cue-controlled evaluation for reliably quantifying privacy-relevant memorization in LLMs.

Federated clustering allows multiple parties to discover patterns in distributed data without sharing raw samples. To reduce overhead, many protocols disclose intermediate centroids during training. While often treated as harmless for efficiency, whether such disclosure compromises privacy remains an open question. Prior analyses modeled the problem as a so-called Hidden Subset Sum Problem (HSSP) and argued that centroid release may be safe, since classical HSSP attacks fail to recover inputs. We revisit this question and uncover a new leakage mechanism: temporal regularities in $k$-means iterations create exploitable structure that enables perfect input reconstruction. Building on this insight, we propose Trajectory-Aware Reconstruction (TAR), an attack that combines temporal assignment information with algebraic analysis to recover exact original inputs. Our findings provide the first rigorous evidence, supported by a practical attack, that centroid disclosure in federated clustering significantly compromises privacy, exposing a fundamental tension between privacy and efficiency.