More Like this

1. Postural analysis reveals persistent changes in paper wasp foundress behavioral state after conspecific challenge

   https://doi.org/10.1002/ece3.10436  

   Legan, Andrew W; Vogt, Caleb C; Sheehan, Michael J (September 2023, Ecology and Evolution)

   Abstract Vigilant animals detect and respond to threats in the environment, often changing posture and movement patterns. Vigilance is modulated not only by predators but also by conspecific threats. In social animals, precisely how conspecific threats alter vigilance behavior over time is relevant to long‐standing hypotheses about social plasticity. We report persistent effects of a simulated conspecific challenge on behavior of wild northern paper wasp foundresses,Polistes fuscatus. During the founding phase of the colony cycle, conspecific wasps can usurp nests from the resident foundress, representing a severe threat. We used automated tracking to monitor the movement and posture ofP. fuscatusfoundresses in response to simulated intrusions. Wasps displayed increased movement, greater bilateral wing extension, and reduced antennal separation after the threat was removed. These changes were not observed after presentation with a wooden dowel. By rapidly adjusting individual behavior after fending off an intruder, paper wasp foundresses might invest in surveillance of potential threats, even when such threats are no longer immediately present. The prolonged vigilance‐like behavioral state observed here is relevant to plasticity of social recognition processes in paper wasps. 

   more » « less
2. Towards Adversarial Attack Resistant Deep Neural Networks

   Tiago A. O. Alves, Sandip Kundu (October 2020, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning)

   null (Ed.)

   Recent publications have shown that neural network based classifiers are vulnerable to adversarial inputs that are virtually indistinguishable from normal data, constructed explicitly for the purpose of forcing misclassification. In this paper, we present several defenses to counter these threats. First, we observe that most adversarial attacks succeed by mounting gradient ascent on the confidence returned by the model, which allows adversary to gain understanding of the classification boundary. Our defenses are based on denying access to the precise classification boundary. Our first defense adds a controlled random noise to the output confidence levels, which prevents an adversary from converging in their numerical approximation attack. Our next defense is based on the observation that by varying the order of the training, often we arrive at models which offer the same classification accuracy, yet they are different numerically. An ensemble of such models allows us to randomly switch between these equivalent models during query which further blurs the classification boundary. We demonstrate our defense via an adversarial input generator which defeats previously published defenses but cannot breach the proposed defenses do to their non-static nature. 

   more » « less
3. Beyond the Glow: Understanding Luminescent Marker Behavior Against Autonomous Vehicle Perception Systems

   Mitra, Arkajyoti; MohajerAnsari, Pedram; Anjum, Afia; Agbaje, Paul; Pesé, Mert; Olufowobi, Habeeb (August 2025, 3rd USENIX Symposium on Vehicle Security and Privacy)

   Autonomous driving (AD) systems rely heavily on accurate lane marker detection for safe navigation, particularly during nighttime or low-light conditions. While luminescent lane markers have been introduced to improve visibility and enhance road safety in these scenarios, they also introduce potential vulnerabilities. This paper investigates these risks by introducing novel luminescent adversarial attacks that exploit the lane detection models used in autonomous vehicles (AVs). We demonstrate how these attacks, targeting deep neural network-based perception models, can manipulate the textural properties of the markers to cause misdetection of lanes, leading to safety violations. Through comprehensive experiments in both digital and physical domains, we systematically expose the vulnerabilities of state-of-the-art lane detection models to adversarial luminescent markers. In our digital experiments, we observe complete model failure in the worst cases and a failure rate of approximately 33% in the best cases. Physical experiments using a device running Openpilot further confirm these risks, underscoring a significant safety threat posed by luminescent adversarial attacks. Our findings emphasize the need for robust defenses to protect AVs from such adversarial threats. 

   more » « less
4. DECENTRALIZED ATTRIBUTION OF GENERATIVE MODELS

   Kim, Changhoon; Ren, Yi; Yang, Yezhou (January 2021, International Conference on Learning Representations)

   Growing applications of generative models have led to new threats such as malicious personation and digital copyright infringement. One solution to these threats is model attribution, i.e., the identification of user-end models where the contents under question are generated from. Existing studies showed empirical feasibility of attribution through a centralized classifier trained on all user-end models. However, this approach is not scalable in reality as the number of models ever grows. Neither does it provide an attributability guarantee. To this end, this paper studies decentralized attribution, which relies on binary classifiers associated with each user-end model. Each binary classifier is parameterized by a user-specific key and distinguishes its associated model distribution from the authentic data distribution. We develop sufficient conditions of the keys that guarantee an attributability lower bound. Our method is validated on MNIST, CelebA, and FFHQ datasets. We also examine the trade-off between generation quality and robustness of attribution against adversarial post-processes. 

   more » « less
5. Towards Trustworthy Autonomous Vehicles with Vision-Language Models under Targeted and Untargeted Adversarial Attacks

   https://doi.org/10.1109/CVPRW67362.2025.00067  

   Fime, Awal Ahmed; Hossain, Md Zarif; Zaman, Saika; Shahid, Abdur R; Imteaj, Ahmed (June 2025, IEEE)

   The integration of autonomous vehicles (AVs) into the transportation sector promises a transformative impact on mobility, safety, and efficiency. Yet, deploying these advanced systems in dynamically complex and unpredictable realworld environments presents substantial challenges, particularly in safeguarding their operational integrity against adversarial attacks. This paper rigorously examines the robustness of Vision-Language Models (VLMs) within AVs, emphasizing their resilience to both targeted and untargeted adversarial threats. We comprehensively evaluate four different vision encoders: CLIP, TeCoA, FARE, and Sim-CLIP. These models are assessed for their ability to maintain accurate and reliable performance when subjected to adversarial manipulations, tailoring a carefully preprocessed dataset designed to generate semantically detailed scene descriptions for enhanced caption generation. This paper explores the performance of these models across various adversarial scenarios, establishing benchmarks for their capability to interpret complex multimodal inputs under subtle adversarial manipulations. The findings reveal notable variances in resilience across the models for various AV-based datasets, with Sim-CLIP outperforming others in terms of robustness and maintaining high accuracy under adversarial conditions. 

   more » « less