A Security-Oriented Lifecycle Model for Large Language Model Systems

Large language models are being integrated into critical infrastructure and enterprise workflows at unprecedented scale,yet the lifecycle frameworks governing their development and operations were designed for operational efficiency rather than security analysis. As a result, security-relevant...

remove-ai-watermarks v0.23.0

Remove AI Watermarks Remove AI provenance marks from images and video you generated yourself: known visible labels such as the Gemini sparkle and vendor text marks; invisible pixel watermarks through diffusion regeneration; C2PA, EXIF, XMP, IPTC, and related AI metadata. Video support covers...

MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory

Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering. We present MutMem, an authorized-mutation protocol in HOM-AIMOS, a persistent...

How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection

Provenance-based intrusion detection systems PIDS frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets tha...

remove-ai-watermarks v0.21.2

Remove AI Watermarks Remove AI provenance marks from images and video you generated yourself: known visible labels such as the Gemini sparkle and vendor text marks; invisible pixel watermarks through diffusion regeneration; C2PA, EXIF, XMP, IPTC, and related AI metadata. Video support covers...

remove-ai-watermarks v0.21.0

Remove AI Watermarks Remove AI provenance marks from images and video you generated yourself: known visible labels such as the Gemini sparkle and vendor text marks; invisible pixel watermarks through diffusion regeneration; C2PA, EXIF, XMP, IPTC, and related AI metadata. Video support covers...

remove-ai-watermarks v0.20.2

Remove AI Watermarks Remove AI provenance marks from images and video you generated yourself: known visible labels such as the Gemini sparkle and vendor text marks; invisible pixel watermarks through diffusion regeneration; C2PA, EXIF, XMP, IPTC, and related AI metadata. Video support covers...

GHSA-HC4M-Q9JH-XW4J nono-cli'scregistry pack verification can fail open when provenance metadata is absent

Summary Registry-installed nono packs are expected to be verified from local provenance metadata before they are used. Two files are relevant: - /.config/nono/packages/lockfile.json - /.config/nono/packages///.nono-trust.bundle Testing shows that nono fails closed when a pack has a trust bundle b...

nono-cli'scregistry pack verification can fail open when provenance metadata is absent

Summary Registry-installed nono packs are expected to be verified from local provenance metadata before they are used. Two files are relevant: - /.config/nono/packages/lockfile.json - /.config/nono/packages///.nono-trust.bundle Testing shows that nono fails closed when a pack has a trust bundle b...

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

Cyber-capable AI agents combine language models with tools, memory, and execution en- vironments to perform multi-step offensive-security tasks. Existing work separately measures cyber capability and catalogs attacks against agent components, but provides less guidance on containing a capable age...

No Snake Oil: Verifying Python Package Builds

Python has become the default language for interacting with AI, with packages being distributed through registries like the Python Package Index PyPI. This creates a need to analyse supply chains comprising such packages. One such analysis is to rebuild packages in order to identify compromised...

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

Large Language Model LLM agents are increasingly used for coding and terminal automation, making shell-command dispatch a high-stakes runtime control point. We study command-level pre-execution mediation for individual shell commands produced by LLM agents under bounded path context. Existing...

When Binaries Talk Back: Representation-Confusion Attacks on LLM-Assisted Reverse Engineering

LLM-assisted reverse-engineering RE systems analyze strings, decompiler output, and tool reports derived from ttacker-controlled binaries. A binary can make data look like instructions or records from one origin look like independent evidence. We call such failures Representation-Confusion Attack...

Embedded Malicious Code

Overview Affected versions of this package are vulnerable to Embedded Malicious Code that conceals a second-stage obfuscated loader. A malicious actor gained push access to the AsyncAPI generator monorepo's next branch. This allowed the attacker to trigger the project's legitimate CI/CD pipeline ...

Embedded Malicious Code

Overview Affected versions of this package are vulnerable to Embedded Malicious Code that conceals a second-stage obfuscated loader. A malicious actor gained push access to the AsyncAPI generator monorepo's next branch. This allowed the attacker to trigger the project's legitimate CI/CD pipeline ...

Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud

Scientific fraud is the instrument of doubt that malicious entities can use to establish controversy in science. Historically, it required the resources of a company: deep pockets, ghostwritten articles, and corrupt academics. Today, Artificial Intelligence AI is increasingly automating scientifi...

GitHub 'Verified' Commits Can Be Rewritten Into New Hashes Without Breaking Signatures

New research shows that a signed Git commit's hash is not the one-of-a-kind name that much of the software world assumes it to be. Given any signed commit, someone without the signing key can mint a second commit with the same files, author, and date, and a valid signature, GitHub still stamps...

Git Hash Chain Malleability

This whitepaper demonstrates that signed Git commits are not uniquely bound to their commit hashes, even when they display a valid "Verified" badge on GitHub. The authors show that attackers can transform the signature encoding of an existing signed commit—without possessing the private signing...

What Changes When Your Software Supply Chain Includes AI Writing Your Code?

Software supply chain security was hard enough. Then AI joined the build pipeline. For five years, "software supply chain security" meant one question: what's in your code? Which open-source packages, which versions, which transitive dependencies three layers deep that nobody chose on purpose?...

REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming

Large language models LLMs are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our ability to measure it. Existing benchmarks for LLM-assisted...