arXiv subjects

David Kohlbrenner

Publications and source records attributed to David Kohlbrenner.

6 recordsLinked to original sources

arXiv2026

Pretraining Data Can Be Poisoned through Computational Propaganda

Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corpora, and has ignored the interaction between poisoned data and data curation pipelines. We demonstrate that poisoning attacks on pretraining data are feasible beyond this limited setting through an existing web-scale content injection mechanism: public discussion interfaces. Additionally, to measure whether malicious content is included after web crawling and data curation, we introduce HalfLife, a novel analysis for estimating adversarial content inclusion in web-crawl based LM training data. We use HalfLife to explore the feasibility of poisoning pretraining corpora at web scale through open discussion interfaces. Our analysis demonstrates the importance of estimating whether poison injections are included in pretraining data, and establishes third-party webpage content as a possible vector for attacking language model pretraining.

cs.AI↗

arXiv2026

SplittingSecrets: A Compiler-Based Defense for Preventing Data Memory-Dependent Prefetcher Side-Channels

Traditional side-channels take advantage of secrets being used as inputs to unsafe instructions, used for memory accesses, or used in control flow decisions. Constant-time programming, which restricts such code patterns, has been widely adopted as a defense against these vulnerabilities. However, new hardware optimizations in the form of Data Memory-dependent Prefetchers (DMP) present in Apple, Intel, and ARM CPUs have shown such defenses are not sufficient. These prefetchers, unlike classical prefetchers, use the content of memory as well as the trace of prior accesses to determine prefetch targets. An adversary abusing such a prefetcher has been shown to be able to mount attacks leaking data-at-rest; data that is never used by the program, even speculatively, in an unsafe manner. In response, this paper introduces SplittingSecrets, a compiler-based tool that can harden software libraries against side-channels arising from DMPs. SplittingSecrets's approach avoids reasoning about the complex internals of different DMPs and instead relies on one key aspect of all DMPs: activation requires data to resemble addresses. To prevent secret data from leaking, SplittingSecrets transforms memory operations to ensure that secrets are never stored in memory in a manner resembling an address, thereby avoiding DMP activation on those secrets. Rather than disable a DMP entirely, SplittingSecrets can provide targeted hardening for only specific secrets entirely in software. We have implemented SplittingSecrets using LLVM, supporting both source-level memory operations and those generated by the compiler backend for the AArch64 architecture, We have analyzed the performance overhead involved in safeguarding secrets from DMP-induced attacks using common primitives in libsodium, a popular cryptographic library when built for Apple M-series CPUs.

cs.CR↗

arXiv2025

Unencrypted Flying Objects: Security Lessons from University Small Satellite Developers and Their Code

Satellites face a multitude of security risks that set them apart from hardware on Earth. Small satellites may face additional challenges, as they are often developed on a budget and by amateur organizations or universities that do not consider security. We explore the security practices and preferences of small satellite teams, particularly university satellite teams, to understand what barriers exist to building satellites securely. We interviewed 8 university satellite club leaders across 4 clubs in the U.S. and perform a code audit of 3 of these clubs' code repositories. We find that security practices vary widely across teams, but all teams studied had vulnerabilities available to an unprivileged, ground-based attacker. Participants foresee many risks of unsecured small satellites and indicate security shortcomings in industry and government. Lastly, we identify a set of considerations for how to build future small satellites securely, in amateur organizations and beyond.

cs.CR↗

arXiv2023

Pentimento: Data Remanence in Cloud FPGAs

Cloud FPGAs strike an alluring balance between computational efficiency, energy efficiency, and cost. It is the flexibility of the FPGA architecture that enables these benefits, but that very same flexibility that exposes new security vulnerabilities. We show that a remote attacker can recover "FPGA pentimenti" - long-removed secret data belonging to a prior user of a cloud FPGA. The sensitive data constituting an FPGA pentimento is an analog imprint from bias temperature instability (BTI) effects on the underlying transistors. We demonstrate how this slight degradation can be measured using a time-to-digital (TDC) converter when an adversary programs one into the target cloud FPGA. This technique allows an attacker to ascertain previously safe information on cloud FPGAs, even after it is no longer explicitly present. Notably, it can allow an attacker who knows a non-secret "skeleton" (the physical structure, but not the contents) of the victim's design to (1) extract proprietary details from an encrypted FPGA design image available on the AWS marketplace and (2) recover data loaded at runtime by a previous user of a cloud FPGA using a known design. Our experiments show that BTI degradation (burn-in) and recovery are measurable and constitute a security threat to commercial cloud FPGAs.

cs.CR↗

arXiv2019

Keystone: An Open Framework for Architecting TEEs

Trusted execution environments (TEEs) are being used in all the devices from embedded sensors to cloud servers and encompass a range of cost, power constraints, and security threat model choices. On the other hand, each of the current vendor-specific TEEs makes a fixed set of trade-offs with little room for customization. We present Keystone -- the first open-source framework for building customized TEEs. Keystone uses simple abstractions provided by the hardware such as memory isolation and a programmable layer underneath untrusted components (e.g., OS). We build reusable TEE core primitives from these abstractions while allowing platform-specific modifications and application features. We showcase how Keystone-based TEEs run on unmodified RISC-V hardware and demonstrate the strengths of our design in terms of security, TCB size, execution of a range of benchmarks, applications, kernels, and deployment models.

cs.CR↗

arXiv2018

Sanctorum: A lightweight security monitor for secure enclaves

Enclaves have emerged as a particularly compelling primitive to implement trusted execution environments: strongly isolated sensitive user-mode processes in a largely untrusted software environment. While the threat models employed by various enclave systems differ, the high-level guarantees they offer are essentially the same: attestation of an enclave's initial state, as well as a guarantee of enclave integrity and privacy in the presence of an adversary. This work describes Sanctorum, a small trusted code base (TCB), consisting of a generic enclave-capable system, which is sufficient to implement secure enclaves akin to the primitive offered by Intel's SGX. While enclaves may be implemented via unconditionally trusted hardware and microcode, as it is the case in SGX, we employ a smaller TCB principally consisting of authenticated, privileged software, which may be replaced or patched as needed. Sanctorum implements a formally verified specification for generic enclaves on an in-order multiprocessor system meeting baseline security requirements, e.g., the MIT Sanctum processor and the Keystone enclave framework. Sanctorum requires trustworthy hardware including a random number generator, a private cryptographic key pair derived via a secure bootstrapping protocol, and a robust isolation primitive to safeguard sensitive information. Sanctorum's threat model is informed by the threat model of the isolation primitive, and is suitable for adding enclaves to a variety of processor systems.

cs.CR↗