The deployment of Large Language Models (LLMs) as assistants in electric grid operations promises to streamline compliance and decision-making but exposes new vulnerabilities to prompt-based adversarial attacks. This paper evaluates the risk of jailbreaking LLMs, i.e., circumventing safety alignments to produce outputs violating regulatory standards, assuming threats from authorized users, such as operators, who craft malicious prompts to elicit non-compliant guidance. Three state-of-the-art LLMs (OpenAI's GPT-4o mini, Google's Gemini 2.0 Flash-Lite, and Anthropic's Claude 3.5 Haiku) were tested against Baseline, BitBypass, and DeepInception jailbreaking methods across scenarios derived from nine NERC Reliability Standards (EOP, TOP, and CIP). In the initial broad experiment, the overall Attack Success Rate (ASR) was 33.1%, with DeepInception proving most effective at 63.17% ASR. Claude 3.5 Haiku exhibited complete resistance (0% ASR), while Gemini 2.0 Flash-Lite was most vulnerable (55.04% ASR) and GPT-4o mini moderately susceptible (44.34% ASR). A follow-up experiment refining malicious wording in Baseline and BitBypass attacks yielded a 30.6% ASR, confirming that subtle prompt adjustments can enhance simpler methods' efficacy.

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to severe consequences, especially in critical applications such as autonomous driving, healthcare, and finance. Detecting and mitigating backdoor attacks is crucial across the lifespan of model's phases, including pre-training, in-training, and post-training. In this paper, we propose Pre-Training Backdoor Mitigation for Federated Learning (FL-PBM), a novel defense mechanism that proactively filters poisoned data on the client side before model training in a federated learning (FL) environment. The approach consists of three stages: (1) inserting a benign trigger into the data to establish a controlled baseline, (2) applying Principal Component Analysis (PCA) to extract discriminative features and assess the separability of the data, (3) performing Gaussian Mixture Model (GMM) clustering to identify potentially malicious data samples based on their distribution in the PCA-transformed space, and (4) applying a targeted blurring technique to disrupt potential backdoor triggers. Together, these steps ensure that suspicious data is detected early and sanitized effectively, thereby minimizing the influence of backdoor triggers on the global model. Experimental evaluations on image-based datasets demonstrate that FL-PBM reduces attack success rates by up to 95% compared to baseline federated learning (FedAvg) and by 30 to 80% relative to state-of-the-art defenses (RDFL and LPSF). At the same time, it maintains over 90% clean model accuracy in most experiments, achieving better mitigation without degrading model performance.

Unlearnable Examples (UEs) serve as a data protection strategy that generates imperceptible perturbations to mislead models into learning spurious correlations instead of underlying semantics. In this paper, we uncover a fundamental vulnerability of UEs that emerges when learning starts from a pretrained model. Crucially, our empirical analysis shows that even when data are protected by carefully crafted perturbations, pretraining priors still furnish rich semantic representations that allow the model to circumvent the shortcuts introduced by UEs and capture genuine features, thereby nullifying unlearnability. To address this, we propose BAIT (Binding Artificial perturbations to Incorrect Targets), a novel bi-level optimization formulation. Specifically, the inner level aims at associating the perturbed samples with real labels to simulate standard data-label alignment, while the outer level actively disrupts this alignment by enforcing a mislabel-perturbation binding that maps samples to designated incorrect targets. This mechanism effectively overrides the semantic guidance of priors, forcing the model to rely on the injected perturbations and consequently preventing the acquisition of true semantics. Extensive experiments on standard benchmarks and multiple pretrained backbones demonstrate that BAIT effectively mitigates the influence of pretraining priors and maintains data unlearnability.

Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent activation-based jailbreaking methods circumvent these safety mechanisms by applying orthogonal projections to remove refusal directions, but these approaches treat refusal as a one-dimensional phenomenon and ignore the rich distributional structure of model activations. We introduce a principled framework based on optimal transport theory that transforms the entire distribution of harmful activations to match harmless ones. By combining PCA with closed-form Gaussian optimal transport, we achieve efficient computation in high-dimensional representation spaces while preserving essential geometric structure. Across six models (Llama-2, Llama-3.1, Qwen-2.5; 7B-32B parameters), our method achieves up to 11% higher attack success rates than state-of-the-art baselines while maintaining comparable perplexity, demonstrating superior preservation of model capabilities. Critically, we discover that layer-selective intervention (applying optimal transport to 1-2 carefully chosen layers at approximately 40-60% network depth) substantially outperforms full-network interventions, revealing that refusal mechanisms may be localized rather than distributed. Our analysis provides new insights into the geometric structure of safety representations and suggests that current alignment methods may be vulnerable to distributional attacks beyond simple direction removal.

The Model Context Protocol (MCP) enables Large Language Models to integrate external tools through structured descriptors, increasing autonomy in decision-making, task execution, and multi-agent workflows. However, this autonomy creates a largely overlooked security gap. Existing defenses focus on prompt-injection attacks and fail to address threats embedded in tool metadata, leaving MCP-based systems exposed to semantic manipulation. This work analyzes three classes of semantic attacks on MCP-integrated systems: (1) Tool Poisoning, where adversarial instructions are hidden in tool descriptors; (2) Shadowing, where trusted tools are indirectly compromised through contaminated shared context; and (3) Rug Pulls, where descriptors are altered after approval to subvert behavior. To counter these threats, we introduce a layered security framework with three components: RSA-based manifest signing to enforce descriptor integrity, LLM-on-LLM semantic vetting to detect suspicious tool definitions, and lightweight heuristic guardrails that block anomalous tool behavior at runtime. Through evaluation of GPT-4, DeepSeek, and Llama-3.5 across eight prompting strategies, we find that security performance varies widely by model architecture and reasoning method. GPT-4 blocks about 71 percent of unsafe tool calls, balancing latency and safety. DeepSeek shows the highest resilience to Shadowing attacks but with greater latency, while Llama-3.5 is fastest but least robust. Our results show that the proposed framework reduces unsafe tool invocation rates without model fine-tuning or internal modification.

Adversarial attacks present a significant risk to the integrity and performance of graph neural networks, particularly in tasks where graph structure and node features are vulnerable to manipulation. In this paper, we present a novel model, called fixed-point iterative graph convolutional network (Fix-GCN), which achieves robustness against adversarial perturbations by effectively capturing higher-order node neighborhood information in the graph without additional memory or computational complexity. Specifically, we introduce a versatile spectral modulation filter and derive the feature propagation rule of our model using fixed-point iteration. Unlike traditional defense mechanisms that rely on additional design elements to counteract attacks, the proposed graph filter provides a flexible-pass filtering approach, allowing it to selectively attenuate high-frequency components while preserving low-frequency structural information in the graph signal. By iteratively updating node representations, our model offers a flexible and efficient framework for preserving essential graph information while mitigating the impact of adversarial manipulation. We demonstrate the effectiveness of the proposed model through extensive experiments on various benchmark graph datasets, showcasing its resilience against adversarial attacks.

Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a thorough investigation into its vulnerabilities to adversarial attacks. Existing work predominantly focuses on training-time attacks or unrealistic scenarios, such as access to policy weights or the ability to train surrogate policies. In this paper, we investigate new vulnerabilities under more challenging and constrained conditions, assuming an adversary can only collect and perturb the observations of deployed agents. We also consider scenarios where the adversary has no access at all (no observations, actions, or weights). Our main approach is to generate perturbations that intentionally misalign how victim agents see their environment. Our approach is empirically validated on three benchmarks and 22 environments, demonstrating its effectiveness across diverse algorithms and environments. Furthermore, we show that our algorithm is sample-efficient, requiring only 1,000 samples compared to the millions needed by previous methods.