TSFMAudit detects pretraining contamination in time series foundation models via probe adaptation dynamics (faster loss drop, smaller backbone shift), tested on 6 models and 187 datasets against 10 LLM-derived baselines.
hub Canonical reference
Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures , url=
Canonical reference. 94% of citing Pith papers cite this work as background.
60
Pith papers citing it
57
external citations · external index
Background
94% of classified citations
hub tools
citation-role summary
background 17
citation-polarity summary
roles
background 15representative citing papers
Cerisier is the first mechanized program logic for modular reasoning about trusted, untrusted, and attested code in capability machines, with a universal contract for untrusted code and demonstrations on secure computation and mutual attestation.
A training-free post-hoc code watermark embeds 24-bit identifiers via multi-channel spread-spectrum encoding over naming conventions and semantic pattern pairs, with majority voting and Reed-Solomon recovery.
Empirical study of real-world vibe-coded apps finds recurring vulnerabilities like placeholder logic and secret exposure caused by AI agent limitations such as memory loss and insufficient security knowledge.
PoisonForge benchmark shows that 1% poisoned examples achieve over 70% attack success rate on targeted tasks across 11 of 12 tested LLMs with under 0.5% leakage to non-target tasks.
A cross-modal alignment attack achieves AUC 0.821 for single-sample black-box membership inference on VLMs such as LLaVA-1.5 by quantifying image-generated caption similarity.
PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.
ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
Zombie domain linkages persist after ownership changes in DNS integrations at rates of 3% in Web PKI, 24% in ENS, and 15% in Maven Central, with validate-once designs accumulating long-term risks while per-use validation prevents them.
PACZero achieves zero mutual information privacy in LLM fine-tuning via sign-quantized subset-aggregated ZO gradients, delivering near non-private accuracy on SST-2 at I=0.
Styx integrates sticky policies with TEEs to enforce data-specific rules throughout the full lifecycle in multi-party collaborative computing.
Grassroots bonds add maturity dates to local cryptocurrencies to enable lending and other instruments via enforceable digital social contracts.
SynBench benchmarks DP text generators across nine datasets and uses a new MIA to show that public pre-training on portions of private data overestimates synthetic text quality and breaks DP privacy bounds.
Flutter achieves 2Δ + ε good-case latency for Byzantine Total Order Broadcast via a new binary consensus called Blink, under partial synchrony with 5f+1 servers.
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
Constrained decoding derived from OpenAPI specifications eliminates hallucinated web API calls in LLM-generated code and substantially improves correctness across 24 models, while retrieval-augmented generation yields inconsistent, model-dependent gains.
Vibe-coded software shows near-zero in-artifact variability; Variability by Regeneration uses the LLM as a derivation engine that regenerates dead-code-free binaries for each product-line variant.
AttackPathGNN introduces a State Interference Graph and conjunction pooling inside a GNN to detect cross-function vulnerabilities in Solidity contracts, reporting 92.3% F1 on SmartBugs Wild.
Incidental prompt cues induce large, systematic shifts in the algorithm families chosen by LLMs during code generation across thousands of controlled trials.
Agent-directed tree search improves LLM performance on Lean formal verification tasks, with context-based orchestration solving more intermediate specs at lower token cost than baseline agents.
TESLA is a practical EM side-channel attack on capacitive touchscreens that achieves 99.3% PIN success, 97.6% keyboard reconstruction, 95% app inference, and 76.8% handwriting character accuracy on commercial phones.
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
GRASP detects anomalies in system provenance graphs via self-supervised executable prediction from two-hop neighborhoods, outperforming prior PIDS on DARPA datasets by identifying all documented attacks where behaviors are learnable plus additional unlabeled suspicious activity.
EASE closes three residual anchors in federated multimodal unlearning using bilateral displacement, cosine-sine decomposition, and forget lock, achieving near-retrain performance on forget and retain data.
citing papers explorer
-
TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models
TSFMAudit detects pretraining contamination in time series foundation models via probe adaptation dynamics (faster loss drop, smaller backbone shift), tested on 6 models and 187 datasets against 10 LLM-derived baselines.
-
Cerisier: A Program Logic for Attestation in a Capability Machine
Cerisier is the first mechanized program logic for modular reasoning about trusted, untrusted, and attested code in capability machines, with a universal contract for untrusted code and demonstrations on secure computation and mutual attestation.
-
Multi-Channel Spread-Spectrum Code Watermarking
A training-free post-hoc code watermark embeds 24-bit identifiers via multi-channel spread-spectrum encoding over naming conventions and semantic pattern pairs, with majority voting and Reed-Solomon recovery.
-
Understanding the (In)Security of Vibe-Coded Applications
Empirical study of real-world vibe-coded apps finds recurring vulnerabilities like placeholder logic and secret exposure caused by AI agent limitations such as memory loss and insufficient security knowledge.
-
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
PoisonForge benchmark shows that 1% poisoned examples achieve over 70% attack success rate on targeted tasks across 11 of 12 tested LLMs with under 0.5% leakage to non-target tasks.
-
Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment
A cross-modal alignment attack achieves AUC 0.821 for single-sample black-box membership inference on VLMs such as LLaVA-1.5 by quantifying image-generated caption similarity.
-
Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.
-
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
-
Zombies in Alternate Realities: The Afterlife of Domain Names in DNS Integrations
Zombie domain linkages persist after ownership changes in DNS integrations at rates of 3% in Web PKI, 24% in ENS, and 15% in Maven Central, with validate-once designs accumulating long-term risks while per-use validation prevents them.
-
PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
PACZero achieves zero mutual information privacy in LLM fine-tuning via sign-quantized subset-aggregated ZO gradients, delivering near non-private accuracy on SST-2 at I=0.
-
Styx: Collaborative and Private Data Processing With TEE-Enforced Sticky Policy
Styx integrates sticky policies with TEEs to enforce data-specific rules throughout the full lifecycle in multi-party collaborative computing.
-
Grassroots Bonds as a Foundation for Market Liquidity
Grassroots bonds add maturity dates to local cryptocurrencies to enable lending and other instruments via enforceable digital social contracts.
-
SynBench: A Benchmark for Differentially Private Text Generation
SynBench benchmarks DP text generators across nine datasets and uses a new MIA to show that public pre-training on portions of private data overestimates synthetic text quality and breaks DP privacy bounds.
-
Fast Byzantine Total Order Broadcast
Flutter achieves 2Δ + ε good-case latency for Byzantine Total Order Broadcast via a new binary consensus called Blink, under partial synchrony with 5f+1 servers.
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding
Constrained decoding derived from OpenAPI specifications eliminates hallucinated web API calls in LLM-generated code and substantially improves correctness across 24 models, while retrieval-augmented generation yields inconsistent, model-dependent gains.
-
Where Did the Variability Go? From Vibe Coding to Product Lines by Regeneration
Vibe-coded software shows near-zero in-artifact variability; Variability by Regeneration uses the LLM as a derivation engine that regenerates dead-code-free binaries for each product-line variant.
-
AttackPathGNN: Cross-function vulnerability detection in smart contracts using state interference graphs and conjunction pooling
AttackPathGNN introduces a State Interference Graph and conjunction pooling inside a GNN to detect cross-function vulnerabilities in Solidity contracts, reporting 92.3% F1 on SmartBugs Wild.
-
The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation
Incidental prompt cues induce large, systematic shifts in the algorithm families chosen by LLMs during code generation across thousands of controlled trials.
-
Automating Formal Verification with Agent-Guided Tree Search
Agent-directed tree search improves LLM performance on Lean formal verification tasks, with context-based orchestration solving more intermediate specs at lower token cost than baseline agents.
-
Capacitive Touchscreens at Risk: A Practical Side-Channel Attack on Smartphones via Electromagnetic Emanations
TESLA is a practical EM side-channel attack on capacitive touchscreens that achieves 99.3% PIN success, 97.6% keyboard reconstruction, 95% app inference, and 76.8% handwriting character accuracy on commercial phones.
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
-
GRASP -- Graph-Based Anomaly Detection Through Self-Supervised Classification
GRASP detects anomalies in system provenance graphs via self-supervised executable prediction from two-hop neighborhoods, outperforming prior PIDS on DARPA datasets by identifying all documented attacks where behaviors are learnable plus additional unlabeled suspicious activity.
-
EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure
EASE closes three residual anchors in federated multimodal unlearning using bilateral displacement, cosine-sine decomposition, and forget lock, achieving near-retrain performance on forget and retain data.
-
CuLifter: Lifting GPU Binaries to Typed IR
CuLifter recovers types from untyped GPU register files via constraint propagation to lift 99.98% of 24,437 functions across 919 cubins to valid LLVM IR.
-
When AI reviews science: Can we trust the referee?
AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.
-
VRSafe: A Secure Virtual Keyboard to Mitigate Keystroke Inference in Virtual Reality
VRSafe adds false positive keystrokes to VR typing data to reduce keystroke inference attack accuracy and includes an efficient malicious login detector.
-
BONSAI: A Mixed-Initiative Workspace for Human-AI Co-Development of Visual Analytics Applications
BONSAI introduces a four-layer architecture and four-phase workflow for human-AI co-development of visual analytics applications, shown in case studies to enable efficient novel tool creation and reconstruction from paper descriptions.
-
AI Slop and the Software Commons
AI slop externalizes private productivity gains onto the software commons, requiring collective Ostrom-style governance rather than individual restraint.
-
KindHML: formal verification of smart contracts based on Hennessy-Milner logic
An encoding of Solidity contracts and first-order Hennessy-Milner logic into Lustre enables Kind 2 model checking of complex temporal properties in smart contracts.
-
GPIR: Enabling Practical Private Information Retrieval with GPUs
GPIR achieves up to 297 times higher throughput than prior GPU PIR systems by fusing operations in stages and using pipelined transposed layouts to cut DRAM traffic during batched lattice-based queries.
-
Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis
A neuro-symbolic pipeline (LLM function summaries + Z3 path checks) injected into CodeQL/Infer finds 54 memory leaks on 3.6M LOC of real C/C++ software, 53 confirmed, versus 19 and 3 for the baselines.
-
Tracking Capabilities for Safer Agents
AI agents can generate code in a capability-safe Scala dialect that statically prevents information leakage and malicious side effects while preserving task performance.
-
Capacitive Touchscreens at Risk: Recovering Handwritten Trajectory on Smartphone via Electromagnetic Emanations
TESLA recovers 2D handwriting trajectories from touchscreen EM emanations on COTS smartphones, achieving 77% character recognition accuracy and 0.74 Jaccard index under realistic conditions.
-
Automated Side-Channel Analysis of Cryptographic Protocol Implementations
A binary-analysis pipeline finds a first-contact privacy leak in WhatsApp Desktop by checking protocol models against instruction-cache side-channel observations.
-
Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing
ANTAP routes queries to AI agents using linear operators learned from benchmark performance instead of text descriptions, blocking description-based attacks but not unknown backdoors.
-
Private training in quantum machine learning
Deterministic gradient-norm bounds in variational QML control DP-SGD clipping bias, so quantum models retain more accuracy than matched classical models under the same privacy budget.
-
Bringing Managed Language Support to WebAssembly with External Library Linking
WALL-E uses external library linking via client-server architecture to support ten managed languages in WebAssembly with hundreds-fold speedup over nested runtimes.
-
Hiding the Trees in the Forest: Building Network Covert Channels with Hash-Based Covert Carrier Filtering
Hash-based key-dependent filtering of covert carriers improves detection resistance in network storage and timing covert channels with low processing overhead.
-
Context-Based Adversarial Attacks on AI Code Generators: Vulnerability Analysis and Implications
Context-based adversarial attacks raise vulnerable code generation in models like GPT-4 and CodeLlama from 3.5% to 37.4%, with 60-100% transferability, and a dual-layer defense reaches 89.1% detection at low false positives.
-
Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions
A lifecycle-based survey of LLM fine-tuning security that reviews attacks and defenses by intervention phase and reports unified empirical findings on model-dependent attack effectiveness and limited defense generalization.
-
Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications
Empirical comparison of alignment ablation methods on a 60-prompt security evaluation suite shows task-only LoRA achieves 0.87 mean security score with 0.13 unsafe compliance.
-
Understanding Student Experiences with TLS Client Authentication
A longitudinal study of 46 CS students finds that configuring and using mTLS client certificates is difficult even for technical users, with only 9% understanding the security implications.
-
Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge
Stacking seven black-box estimators into a meta-classifier reveals persistent membership leakage in differentially private federated learning models at epsilon=200 on NIST genomics data, outperforming single-signal baselines.
-
Evasion Under Blockchain Sanctions
Empirical analysis of 1.07 billion Ethereum transactions shows sanctions cut Tornado Cash deposits by 71% yet the mixer remained central to most security incidents, exposing three structural enforcement weaknesses.
-
ML-Powered LDAP Reconnaissance Detection using Weak Supervision
Weakly supervised ML classifier and hypothesis-testing signature mining detect LDAP reconnaissance at 65% TPR and 81.48% field precision.
-
Quantifying the Impact of Stealthy BLE Spam & Flooding Attacks on IoT Environments
Develops a quantitative foundation for BLE flooding attack impacts on IoT and proposes an agility-based deterrence strategy.
-
Opportunities and Challenges in Securely Reusing and Repurposing Mobile Devices
Experiments on PinePhone show vendor-controlled security mechanisms hinder secure repurposing of mobile devices by complicating reconstruction of trust anchors, leading to requirements for secure reuse.
-
How to Compare the Security of Code Written by Humans to LLM-generated Code
Proposes and validates via feasibility study an open-source automated framework for reproducible, species-fair security comparisons of human-written, LLM-generated, and hybrid code.
-
Building Digital Societies as Ecosystems: How Recognition and Repeat Relationships Sustain Cross-Community Work in Open Source
Cross-boundary collaboration in open source is sustained by a thin carrier layer of contributors and repeat relationships that increase pull request acceptance rates from 42% to 87%.