The goal of this study is to understand practitioners'decision making process and security considerations in selecting and integrating AI components through an exploratory semi-structured interview study, and distill the findings into actionable recommendations for AI adopters, model providers, and researchers.
Mahzabin Tamanna, Elizabeth Lin, Sparsha Gowda et al.· 0 citations
Genomic language models (GLMs) have emerged as powerful tools for learning representations of DNA sequences, enabling advances in variant prediction, regulatory element identification, and cross-task transfer learning. However, as these models are increasingly trained or fine-tuned on sensitive genomic cohorts, they risk memorizing specific sequences from their training data, raising serious concerns around privacy, data leakage, and regulatory compliance. Despite growing awareness of memorization risks in general-purpose language models, little systematic evaluation exists for these risks in the genomic domain, where data exhibit unique properties such as a fixed nucleotide alphabet, strong biological structure, and individual identifiability. We present a comprehensive, multi-vector privacy evaluation framework designed to quantify memorization risks in GLMs. Our approach integrates three complementary risk assessment methodologies: perplexity-based detection, canary sequence extraction, and membership inference. These are combined into a unified evaluation pipeline that produces a worst-case memorization risk score. To enable controlled evaluation, we plant canary sequences at varying repetition rates into both synthetic and real genomic datasets, allowing precise quantification of how repetition and training dynamics influence memorization. We evaluate our framework across multiple GLM architectures, examining the relationship between sequence repetition, model capacity, and memorization risk. Our results establish that GLMs exhibit measurable memorization and that the degree of memorization varies across architectures and training regimes. These findings reveal that no single attack vector captures the full scope of memorization risk, underscoring the need for multi-vector privacy auditing as a standard practice for genomic AI systems.
Alexander Nemecek, Wenbiao Li, Xiaoqian Jiang et al.· 0 citations
Feature-Community-guided DICE (FCom-DICE), a perturbation strategy built on DICE that rewires a set of structurally influential edges and adjusts node features to reduce the distinctiveness exploited by GNN message passing is introduced.
Dalyapraz Manatova, P. Moriano, L. J. Camp· 0 citations
The proposed Diff-DDoS framework, a three-phase framework for realistic attack synthesis and robust detection using tabular diffusion models, supports tabular diffusion models for stress-testing and hardening intrusion detectors in data-scarce 5G cyber-physical deployments.
Bilal Hussain, Xiao Tang, Qinghe Du et al.· 0 citations
This work proposes MemCatalyst, a set of data poisoning tools, aiming to amplify the data auditing performance on VLMs, and forces VLMs to over-learn specific inconsistencies between image features and textual semantics during training, thereby increasing their susceptibility to membership information auditing.
Xukun Luan, Jinyan Liu, Yuhui Gong et al.· 0 citations
Reflex-Guard is introduced, a lightweight guardrail that runs locally that uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers that enable high-accuracy prompt safety filtering with much lower latency than existing solutions.
Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon et al.· 0 citations
Motivated by a conjecture of Vaikuntanathan and Zamir, we study the pseudo-mixing of Kac's walk on $\mathrm{SO}(n)$: whether short trajectories are indistinguishable from Haar measure by low-complexity tests. We prove that the first $k$ columns mix in Wasserstein distance in $O(n(k+\log n)\log n)$ steps for fixed accuracy, resolving a conjecture of Oliveira. Combining this with a representation-theoretic variance bound, we show that if $T=\omega(nk(k+\log n)\log n)$, then every degree-$k$ polynomial normalized to have unit Haar variance has expectation under the $T$-step law within $o(1)$ of its Haar expectation. As an application, we show that this pseudo-mixing estimate can be used to prove the effectiveness of a fast Johnson--Lindenstrauss transform with the usual target dimension.
N. Pillai, Aaron Smith, Vinod Vaikuntanathan· 0 citations
A comparative study of four audits applicable to pre-trained, black-box face generators, which consistently reveal substantial identity distinguishability while reporting markedly different epsilon estimates that reflect each method's distinct assumptions and finite-sample treatment.
Arman Zareian Jahromi, Vishnu Bondalakunta, Mohammad Akbar Bin Shah et al.· 0 citations
A DT-based IDS that jointly models physical relationships among decoded powertrain signals and identifies attacks through residuals between predicted and observed behavior shows promise for detecting stealthy payload-level CAN attacks that preserve normal communication patterns, supporting behavior-based cybersecurity for connected and automated vehicles.
Araf Rahman, M. Salek, Mashrur Chowdhury· 0 citations
LLM-based code generation is now embedded in mission-critical pipelines, but defenses against vulnerable output remain post-hoc -- static analyzers, fine-tuned classifiers, or an LLM judge that screen completed code, ignoring the generating model's own internal state. We test a narrower, directly measurable question: when an LLM reads a piece of C/C++ code as context, do its hidden activations already carry a signal about that code's vulnerability status? We extract last prefill token activations from four LLMs (Granite-4.1-8B, Qwen3.5-9B, Qwen3.6-27B, Gemma-4-12B) across three model families and train MLP probes on these activations. We evaluate them on four function-level C/C++ benchmarks (Devign, Big-Vul, Draper VDISC, PrimeVul). Our probes achieve 41.7\% average F1 using 13.4--16.0M-parameter probes -- under 0.2\% of base-model size. On Devign, the best probe (Qwen3.5-9B, 68.8\% F1) matches the published fine-tuned-classifier SOTA (67.9\%) despite reading only a frozen, general-purpose LLM's activations; on the harder, more imbalanced benchmarks (Big-Vul, Draper VDISC, PrimeVul) probes trail SOTA substantially. This is early evidence that a coding LLM's own representation of arbitrary code is informative about that code's vulnerability status, motivating further work toward lightweight, model-native vulnerability screening.
This work proposes MITRE-SAGE, a multi-agent retrieval-augmented generation framework that integrates semantic and structural cybersecurity knowledge to improve the reliability and interpretability of LLM-based QA systems and proposes MITRE-QA, a comprehensive benchmark for evaluating LLMs across diverse cybersecurity knowledge tasks.
Ali Habibzadeh, Farid Feyzi, Reza Ebrahimi Atani· 0 citations
PANDA is a scalable system that uses zero-knowledge proofs to prove the robustness and fairness properties of a model without revealing its private parameters, and can generate proofs of local robustness for neural networks with more than 2.9M parameters in 5 minutes, and can verify them in 10 seconds.
Youwei Zhong, Ben Merbaum, Timos Antonopoulos et al.· 0 citations
