Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccuracies to gradually solidify into system-level false consensus through iteration. Such risks are difficult to trace since errors can propagate and amplify through message dependencies. Existing protections often rely on single-agent validation or require modifications to the collaboration architecture, which can weaken effective information flow and may not align with natural collaboration processes in real tasks. To address this, we propose a propagation dynamics model tailored for LLM-MAS that abstracts collaboration as a directed dependency graph and provides an early-stage risk criterion to characterize amplification risk. Through experiments on six mainstream frameworks, we identify three vulnerability classes: cascade amplification, topological sensitivity, and consensus inertia. We further instantiate an attack where injecting just a single atomic error seed leads to widespread failure. In response, we introduce a genealogy-graph-based governance layer, implemented as a message-layer plugin, that suppresses both endogenous and exogenous error amplification without altering the collaboration architecture. Experiments show that this approach raises the defense success rate from a baseline of 0.32 to over 0.89 and significantly mitigates the cascading spread of minor errors.

Secure aggregation is a foundational building block of privacy-preserving learning, yet achieving robustness under adversarial behavior remains challenging. Modern systems increasingly adopt the shuffle model of differential privacy (Shuffle-DP) to locally perturb client updates and globally anonymize them via shuffling for enhanced privacy protection. However, these perturbations and anonymization distort gradient geometry and remove identity linkage, leaving systems vulnerable to adversarial poisoning attacks. Moreover, the shuffler, typically a third party, can be compromised, undermining security against malicious adversaries. To address these challenges, we present Robust Aggregation in Noise (RAIN), a unified framework that reconciles privacy, robustness, and verifiability under Shuffle-DP. At its core, RAIN adopts sign-space aggregation to robustly measure update consistency and limit malicious influence under noise and anonymization. Specifically, we design two novel secret-shared protocols for shuffling and aggregation that operate directly on additive shares and preserve Shuffle-DP's tight privacy guarantee. In each round, the aggregated result is verified to ensure correct aggregation and detect any selective dropping, achieving malicious security with minimal overhead. Extensive experiments across comprehensive benchmarks show that RAIN maintains strong privacy guarantees under Shuffle-DP and remains robust to poisoning attacks with negligible degradation in accuracy and convergence. It further provides real-time integrity verification with complete tampering detection, while achieving up to 90x lower communication cost and 10x faster aggregation compared with prior work.

Watermarking is a technical alternative to safeguarding intellectual property and reducing misuse. Existing methods focus on optimizing watermarked latent variables to balance watermark robustness and fidelity, as Latent diffusion models (LDMs) are considered a powerful tool for generative tasks. However, reliance on computationally intensive heuristic optimization for iterative signal refinement results in high training overhead and local optima entrapment.To address these issues, we propose an \underline{A}na\underline{l}ytical Watermark\underline{i}ng Framework for Controllabl\underline{e} Generatio\underline{n} (ALIEN). We develop the first analytical derivation of the time-dependent modulation coefficient that guides the diffusion of watermark residuals to achieve controllable watermark embedding pattern.Experimental results show that ALIEN-Q outperforms the state-of-the-art by 33.1\% across 5 quality metrics, and ALIEN-R demonstrates 14.0\% improved robustness against generative variant and stability threats compared to the state-of-the-art across 15 distinct conditions. Code can be available at https://anonymous.4open.science/r/ALIEN/.

Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically validate the Trust-Vulnerability Paradox (TVP): increasing inter-agent trust to enhance coordination simultaneously expands risks of over-exposure and over-authorization. To investigate this paradox, we construct a scenario-game dataset spanning 3 macro scenes and 19 sub-scenes, and run extensive closed-loop interactions with trust explicitly parameterized. Using Minimum Necessary Information (MNI) as the safety baseline, we propose two unified metrics: Over-Exposure Rate (OER) to detect boundary violations, and Authorization Drift (AD) to capture sensitivity to trust levels. Results across multiple model backends and orchestration frameworks reveal consistent trends: higher trust improves task success but also heightens exposure risks, with heterogeneous trust-to-risk mappings across systems. We further examine defenses such as Sensitive Information Repartitioning and Guardian-Agent enablement, both of which reduce OER and attenuate AD. Overall, this study formalizes TVP, establishes reproducible baselines with unified metrics, and demonstrates that trust must be modeled and scheduled as a first-class security variable in multi-agent system design.

Federated Learning (FL) enables collaborative training while preserving privacy, yet Gradient Inversion Attacks (GIAs) pose severe threats by reconstructing private data from shared gradients. In realistic FedAvg scenarios with multi-step updates, existing surrogate methods like SME rely on linear interpolation to approximate client trajectories for privacy leakage. However, we demonstrate that linear assumptions fundamentally underestimate SGD's nonlinear complexity, encountering irreducible approximation barriers in non-convex landscapes with only one-dimensional expressiveness. We propose Non-Linear Surrogate Model Extension (NL-SME), the first framework introducing learnable quadratic Bézier curves for trajectory modeling in GIAs against FL. NL-SME leverages $|w|+1$-dimensional control point parameterization combined with dvec scaling and regularization mechanisms to achieve superior approximation accuracy. Extensive experiments on CIFAR-100 and FEMNIST demonstrate NL-SME significantly outperforms baselines across all metrics, achieving 94\%--98\% performance gaps and order-of-magnitude improvements in cosine similarity loss while maintaining computational efficiency. This work exposes critical privacy vulnerabilities in FL's multi-step paradigm and provides insights for robust defense development.

Defending backdoor attacks in Federated Learning (FL) under heterogeneous client data distributions encounters limitations balancing effectiveness and privacy-preserving, while most existing methods highly rely on the assumption of homogeneous client data distributions or the availability of a clean serve dataset. In this paper, we propose an FL backdoor defense framework, named CLIP-Fed, that utilizes the zero-shot learning capabilities of vision-language pre-training models. Our scheme overcomes the limitations of Non-IID imposed on defense effectiveness by integrating pre-aggregation and post-aggregation defense strategies. CLIP-Fed aligns the knowledge of the global model and CLIP on the augmented dataset using prototype contrastive loss and Kullback-Leibler divergence, so that class prototype deviations caused by backdoor samples are ensured and the correlation between trigger patterns and target labels is eliminated. In order to balance privacy-preserving and coverage enhancement of the dataset against diverse triggers, we further construct and augment the server dataset via using the multimodal large language model and frequency analysis without any client samples. Extensive experiments on representative datasets evidence the effectiveness of CLIP-Fed. Comparing to other existing methods, CLIP-Fed achieves an average reduction in Attack Success Rate, {\em i.e.}, 2.03\% on CIFAR-10 and 1.35\% on CIFAR-10-LT, while improving average Main Task Accuracy by 7.92\% and 0.48\%, respectively. Our codes are available at https://anonymous.4open.science/r/CLIP-Fed.

Federated Unlearning (FU) has emerged as a promising solution to respond to the right to be forgotten of clients, by allowing clients to erase their data from global models without compromising model performance. Unfortunately, researchers find that the parameter variations of models induced by FU expose clients' data information, enabling attackers to infer the label of unlearning data, while label inference attacks against FU remain unexplored. In this paper, we introduce and analyze a new privacy threat against FU and propose a novel label inference attack, ULIA, which can infer unlearning data labels across three FU levels. To address the unique challenges of inferring labels via the models variations, we design a gradient-label mapping mechanism in ULIA that establishes a relationship between gradient variations and unlearning labels, enabling inferring labels on accumulated model variations. We evaluate ULIA on both IID and non-IID settings. Experimental results show that in the IID setting, ULIA achieves a 100% Attack Success Rate (ASR) under both class-level and client-level unlearning. Even when only 1% of a user's local data is forgotten, ULIA still attains an ASR ranging from 93% to 62.3%.