We evaluate the effectiveness of child filtering to prevent the misuse of text-to-image (T2I) models to create child sexual abuse material (CSAM). First, we capture the complexity of preventing CSAM generation using a game-based security definition. Second, we show that current detection methods cannot remove all children from a dataset. Third, using an ethical proxy for CSAM (a child wearing glasses, hereafter, CWG), we show that even when only a small percentage of child images are left in the training dataset, there exist prompting strategies that generate CWG from a child-filtered T2I model using only a few more queries than when the model is trained on the unfiltered data. Fine-tuning the filtered model on child images further reduces the additional query overhead. We also show that reintroducing a concept is possible via fine-tuning even if filtering is perfect. Our results demonstrate that current filtering methods offer limited protection to closed-weight models and no protection to open-weight models, while reducing the generality of the model by hindering the generation of child-related concepts or changing their representation. We conclude by outlining challenges in conducting evaluations that establish robust evidence on the impact of AI safety mitigations for CSAM.
Large Language Models (LLMs) display notable variation in multilingual behavior, yet the role of genealogical language structure in shaping this variation remains underexplored. In this paper, we investigate whether LLMs exhibit sensitivity to linguistic genera by extending prior analyses on the MultiQ dataset. We first check if models prefer to switch to genealogically related languages when prompt language fidelity is not maintained. Next, we investigate whether knowledge consistency is better preserved within than across genera. We show that genus-level effects are present but strongly conditioned by training resource availability. We further observe distinct multilingual strategies across LLMs families. Our findings suggest that LLMs encode aspects of genus-level structure, but training data imbalances remain the primary factor shaping their multilingual performance.
In this note, we provide proven estimates for the complexity of the SupportMinors Modeling, mostly confirming the heuristic complexity estimates contained in the original article (Bardet (2020) Improvements of algebraic attacks for solving the rank decoding and MinRank problems. In: Advances in cryptology. Springer, pp 507–536).
The Iridium Low Earth Orbit (LEO) satellite constellation remains a unique provider of global communications for critical industries, governments, and private users, serving over 2.5 million active subscribers despite recent market competition. In contrast to terrestrial wireless standards such as 3GPP, Iridium protocol specifications are proprietary and have not undergone rigorous, public, and systematic security evaluation. In this work, we present the first comprehensive security analysis of Iridium authentication and radio link protocols. We reverse engineer Iridium SIM-based authentication mechanism and demonstrate that the secret key can be extracted from the SIM card, enabling full device cloning and impersonation attacks. Leveraging a month-long dataset of Iridium up- and downlink satellite traffic, we further show that nearly all signaling and radio communication protocols currently in use lack encryption, resulting in the exposure of sensitive information in cleartext over the air such as login credentials and large volumes of personal data. Finally, we develop custom software-defined radio (SDR) tools to carry out spoofing and jamming attacks, revealing that modestly equipped adversaries can inject falsified messages or disrupt the Iridium service locally due to the absence of source authentication. Our findings uncover systemic vulnerabilities in the Iridium radio link and highlight the urgent need for users of critical applications to transition to more secure communication radio links.
The adoption of Electric Vehicles (EVs) is happening at a rapid pace. To ensure fast and safe charging, complex communication is required between the vehicle and the charging station. In the globally used Combined Charging System (CCS), this communication is carried over the HomePlug Green PHY (HPGP) physical layer. However, HPGP is known to suffer from wireless leakage, which may expose this data link to nearby attackers. In this paper, we examine active wireless attacks against CCS, and study the impact they can have. We present the first real-time Software-Defined Radio (SDR) implementation of HPGP, granting unprecedented access to the communications within the charging cables. We analyze the characteristics of 2,750 real-world charging sessions to understand the timing constraints for hijacking. Using novel techniques to increase the attacks' reliability, we design a robust wireless Man-in-the-Middle evaluation framework for CCS. We demonstrate full control over TLS usage and CCS protocol version negotiation, including TLS stripping attacks. We investigate how real devices respond to safety-critical MitM attacks, which modify power delivery information, and found target vehicles to be highly permissive. First, we caused a vehicle to display charging power exceeding 900 kW on the dashboard, while receiving only 40 kW. Second, we remotely overcharged a vehicle, at twice the requested current for 17 seconds before the vehicle triggered the emergency shutdown. Finally, we propose a backwards-compatible, downgrade-proof protocol extension to mitigate the underlying vulnerabilities.
