Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to task drift; deviations from a user's intended instruction due to injected secondary prompts. Recent work has shown that linear probes trained on activation deltas of LLMs' hidden layers can effectively detect such drift. In this paper, we evaluate the robustness of these detectors against adversarially optimised suffixes. We generate universal suffixes that cause poisoned inputs to evade detection across multiple probes simultaneously. Our experiments on Phi-3 3.8B and Llama-3 8B show that a single suffix can achieve high attack success rates; up to 93.91% and 99.63%, respectively, when all probes must be fooled, and nearly perfect success (>90%) under majority vote setting. These results demonstrate that activation delta-based task drift detectors are highly vulnerable to adversarial suffixes, highlighting the need for stronger defences against adaptive attacks. We also propose a defence technique where we generate multiple suffixes and randomly append one of them to the prompts while making forward passes of the LLM and train logistic regression models with these activations. We found this approach to be highly effective against such attacks.

Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency to memorize training data raises serious privacy and intellectual property concerns. A key threat is the membership inference attack (MIA), which aims to determine whether a given sample was included in the model's training set. Existing MIAs for LLMs rely primarily on output confidence scores or embedding-based features, but these signals are often brittle, leading to limited attack success. We introduce AttenMIA, a new MIA framework that exploits self-attention patterns inside the transformer model to infer membership. Attention controls the information flow within the transformer, exposing different patterns for memorization that can be used to identify members of the dataset. Our method uses information from attention heads across layers and combines them with perturbation-based divergence metrics to train an effective MIA classifier. Using extensive experiments on open-source models including LLaMA-2, Pythia, and Opt models, we show that attention-based features consistently outperform baselines, particularly under the important low-false-positive metric (e.g., achieving up to 0.996 ROC AUC & 87.9% TPR@1%FPR on the WikiMIA-32 benchmark with Llama2-13b). We show that attention signals generalize across datasets and architectures, and provide a layer- and head-level analysis of where membership leakage is most pronounced. We also show that using AttenMIA to replace other membership inference attacks in a data extraction framework results in training data extraction attacks that outperform the state of the art. Our findings reveal that attention mechanisms, originally introduced to enhance interpretability, can inadvertently amplify privacy risks in LLMs, underscoring the need for new defenses.

Neuromorphic computing mimics brain-inspired mechanisms through spiking neurons and energy-efficient processing, offering a pathway to efficient in-memory computing (IMC). However, these advancements raise critical security and privacy concerns. As the adoption of bio-inspired architectures and memristive devices increases, so does the urgency to assess the vulnerability of these emerging technologies to hardware and software attacks. Emerging architectures introduce new attack surfaces, particularly due to asynchronous, event-driven processing and stochastic device behavior. The integration of memristors into neuromorphic hardware and software implementations in spiking neural networks offers diverse possibilities for advanced computing architectures, including their role in security-aware applications. This survey systematically analyzes the security landscape of neuromorphic systems, covering attack methodologies, side-channel vulnerabilities, and countermeasures. We focus on both hardware and software concerns relevant to spiking neural networks (SNNs) and hardware primitives, such as Physical Unclonable Functions (PUFs) and True Random Number Generators (TRNGs) for cryptographic and secure computation applications. We approach this analysis from diverse perspectives, from attack methodologies to countermeasure strategies that integrate efficiency and protection in brain-inspired hardware. This review not only maps the current landscape of security threats but provides a foundation for developing secure and trustworthy neuromorphic architectures.

Spiking neural networks (SNNs) have emerged as prominent candidates for embedded and edge AI. Their inherent low power consumption makes them far more efficient than conventional ANNs in scenarios where energy budgets are tightly constrained. In parallel, federated learning (FL) has become the prevailing training paradigm in such settings, enabling on-device learning while limiting the exposure of raw data. However, gradient inversion attacks represent a critical privacy threat in FL, where sensitive training data can be reconstructed directly from shared gradients. While this vulnerability has been widely investigated in conventional ANNs, its implications for SNNs remain largely unexplored. In this work, we present the first comprehensive empirical study of gradient leakage in SNNs across diverse data domains. SNNs are inherently non-differentiable and are typically trained using surrogate gradients, which we hypothesized would be less correlated with the original input and thus less informative from a privacy perspective. To investigate this, we adapt different gradient leakage attacks to the spike domain. Our experiments reveal a striking contrast with conventional ANNs: whereas ANN gradients reliably expose salient input content, SNN gradients yield noisy, temporally inconsistent reconstructions that fail to recover meaningful spatial or temporal structure. These results indicate that the combination of event-driven dynamics and surrogate-gradient training substantially reduces gradient informativeness. To the best of our knowledge, this work provides the first systematic benchmark of gradient inversion attacks for spiking architectures, highlighting the inherent privacy-preserving potential of neuromorphic computation.

Federated Learning (FL) enables decentralized model training across multiple clients without exposing local data, but its distributed feature makes it vulnerable to backdoor attacks. Despite early FL backdoor attacks modifying entire models, recent studies have explored the concept of backdoor-critical (BC) layers, which poison the chosen influential layers to maintain stealthiness while achieving high effectiveness. However, existing BC layers approaches rely on rule-based selection without consideration of the interrelations between layers, making them ineffective and prone to detection by advanced defenses. In this paper, we propose POLAR (POlicy-based LAyerwise Reinforcement learning), the first pipeline to creatively adopt RL to solve the BC layer selection problem in layer-wise backdoor attack. Different from other commonly used RL paradigm, POLAR is lightweight with Bernoulli sampling. POLAR dynamically learns an attack strategy, optimizing layer selection using policy gradient updates based on backdoor success rate (BSR) improvements. To ensure stealthiness, we introduce a regularization constraint that limits the number of modified layers by penalizing large attack footprints. Extensive experiments demonstrate that POLAR outperforms the latest attack methods by up to 40% against six state-of-the-art (SOTA) defenses.

AI-generated image (AIGI) detection and source model attribution remain central challenges in combating deepfake abuses, primarily due to the structural diversity of generative models. Current detection methods are prone to overfitting specific forgery traits, whereas source attribution offers a robust alternative through fine-grained feature discrimination. However, synthetic image attribution remains constrained by the scarcity of large-scale, well-categorized synthetic datasets, limiting its practicality and compatibility with detection systems. In this work, we propose a new paradigm for image attribution called open-set, few-shot source identification. This paradigm is designed to reliably identify unseen generators using only limited samples, making it highly suitable for real-world application. To this end, we introduce OmniDFA (Omni Detector and Few-shot Attributor), a novel framework for AIGI that not only assesses the authenticity of images, but also determines the synthesis origins in a few-shot manner. To facilitate this work, we construct OmniFake, a large class-aware synthetic image dataset that curates $1.17$ M images from $45$ distinct generative models, substantially enriching the foundational resources for research on both AIGI detection and attribution. Experiments demonstrate that OmniDFA exhibits excellent capability in open-set attribution and achieves state-of-the-art generalization performance on AIGI detection. Our dataset and code will be made available.

Federated Learning (FL) is a distributed learning paradigm designed to address privacy concerns. However, FL is vulnerable to poisoning attacks, where Byzantine clients compromise the integrity of the global model by submitting malicious updates. Robust aggregation methods have been widely adopted to mitigate such threats, relying on the core assumption that malicious updates are inherently out-of-distribution and can therefore be identified and excluded before aggregating client updates. In this paper, we challenge this underlying assumption by showing that a model can be poisoned while keeping malicious updates within the main distribution. We propose Chameleon Poisoning (CHAMP), an adaptive and evasive poisoning strategy that exploits side-channel feedback from the aggregation process to guide the attack. Specifically, the adversary continuously infers whether its malicious contribution has been incorporated into the global model and adapts accordingly. This enables a dynamic adjustment of the local loss function, balancing a malicious component with a camouflaging component, thereby increasing the effectiveness of the poisoning while evading robust aggregation defenses. CHAMP enables more effective and evasive poisoning, highlighting a fundamental limitation of existing robust aggregation defenses and underscoring the need for new strategies to secure federated learning against sophisticated adversaries. Our approach is evaluated in two datasets reaching an average increase of 47.07% in attack success rate against nine robust aggregation defenses.

Large Language Models (LLMs) are aligned to meet ethical standards and safety requirements by training them to refuse answering harmful or unsafe prompts. In this paper, we demonstrate how adversaries can exploit LLMs' alignment to implant bias, or enforce targeted censorship without degrading the model's responsiveness to unrelated topics. Specifically, we propose Subversive Alignment Injection (SAI), a poisoning attack that leverages the alignment mechanism to trigger refusal on specific topics or queries predefined by the adversary. Although it is perhaps not surprising that refusal can be induced through overalignment, we demonstrate how this refusal can be exploited to inject bias into the model. Surprisingly, SAI evades state-of-the-art poisoning defenses including LLM state forensics, as well as robust aggregation techniques that are designed to detect poisoning in FL settings. We demonstrate the practical dangers of this attack by illustrating its end-to-end impacts on LLM-powered application pipelines. For chat based applications such as ChatDoctor, with 1% data poisoning, the system refuses to answer healthcare questions to targeted racial category leading to high bias ($ΔDP$ of 23%). We also show that bias can be induced in other NLP tasks: for a resume selection pipeline aligned to refuse to summarize CVs from a selected university, high bias in selection ($ΔDP$ of 27%) results. Even higher bias ($ΔDP$~38%) results on 9 other chat based downstream applications.