Dr. Pankaj Malik, Mohit Kapoor, Akshat Gupta, Aman Singhai · 5 authors
The rapid expansion of decentralized finance (DeFi) platforms has been accompanied by a surge in rug pull scams, where malicious actors exploit liquidity pools and abandon projects, causing substantial investor losses. Existing detection approaches are largely centralized and platform-specific, limiting their effectiveness due to privacy constraints, fragmented data sources, and the dynamic behavior of blockchain ecosystems. This paper proposes a novel Federated Time-Series Learning (FTSL) framework for cross-platform rug pull detection that enables collaborative model training without sharing raw transaction data. The proposed system integrates federated learning with advanced time-series modeling to capture temporal patterns in token price volatility, liquidity changes, transaction frequency, and smart contract activities. A hybrid deep learning architecture combining Long Short-Term Memory (LSTM) networks with an attention mechanism is employed to effectively learn sequential dependencies and identify early indicators of fraudulent behavior. The federated setup ensures privacy preservation while enabling knowledge sharing across multiple decentralized platforms. Experimental results on multi-chain DeFi datasets demonstrate that the proposed FTSL model achieves 96.3% detection accuracy, outperforming traditional centralized models (91.2%) and single-platform approaches (88.7%). The model also improves precision (95.1%), recall (94.6%), and F1-score (94.8%), indicating robust and balanced performance. Furthermore, the system is capable of detecting rug pull events 6–12 hours earlier than baseline methods, providing critical early warning signals. Communication overhead is reduced by approximately 28% through optimized federated aggregation, while maintaining scalability across heterogeneous platforms. These findings highlight that Federated Time-Series Learning offers a scalable, privacy-preserving, and highly effective solution for real-time rug pull detection, contributing to enhanced security, transparency, and trust in decentralized financial ecosystems.
Recently, extensive research has focused on addressing the unique challenges of smart contract fuzzing. Nevertheless, existing fuzzers still struggle to generate adequate function call arguments that can explore the deep smart contract states. In this paper, we introduce novel classes of argument constraints that capture the inter-argument relationships required to exercise meaningful contract logic. We propose a static analysis algorithm to extract these constraints from Solidity source code. In addition, we design a constraint-aware argument mutation strategy that leverages the identified constraints to guide test case generation for smart contract fuzzing. We implement our approach in a fuzzer named IConFuzz. Our evaluation on realistic benchmarks with integer overflow, suicidal contract, and ether leakage vulnerabilities demonstrates that IConFuzz outperforms state-of-the-art testing tools in both the number of bugs discovered and the speed of bug detection.
Integrating artificial intelligence (AI) like the large language model (LLM) for smart contract auto-generation standardises performance and security, reduces human error, and offers accessibility for non-developers.In decentralised autonomous systems (DASs) like decentralised finance (DeFi), the ability to AI-generate smart contracts strengthens the decentralisation and automation characteristics of the applications.In order to increase the effectiveness of a smart contract's fully decentralised and autonomous development, this study benchmarks gas-saving patterns in AI-generated DeFi smart contracts.Three DeFI smart contract development scenarios: token generation (ERC-20), tokenised vault (ERC-4626), and flash loan (ERC-3156), and the state-of-the-art LLMs (Code Llama and Code Llama -Python) are explored to study the gas-saving patterns of AI-generated smart contracts.These results help optimise DeFi smart contracts created by AI regarding gas fees for the same operations.
Everybody throws around the term "blockchain" these days, like it's some secret sauce. But smart contracts are where things actually start to get interesting. Forget endless forms and relying on someone's handshake; smart contracts handle things automatically. They're just coded agreements that trigger themselves no middlemen, no second-guessing if someone's being honest. You know what you're getting. This review looks at how smart contracts are changing the game in two touchy areas: healthcare and voting, where trust and privacy can't be taken lightly. Dealing with healthcare is usually a hassle. People lose records, insurance companies bounce you around, and privacy feels flimsy. With smart contracts, you're in charge of your data, claims happen faster, and private info stays private. Doctors can share what they need to, without breaking the rules. Voting? It's had trust issues forever people aren't sure their votes count for anything. Smart contracts clean things up. They make voting more transparent, help stop fraud, and lock down the results. You can check your ballot and know nobody's changing numbers behind the scenes. Of course, it's not all smooth sailing blockchain slows down when things get big, laws haven't caught up, some of the interfaces are confusing, and big organizations don't like change. This paper covers what works, what needs help, and where things could go next.
We present Processual Memory Architecture (PMA), a computational framework that unifies data storage and computation by representing all information as transformation functions rather than static state, rendering the traditional ontological distinction between them architecturally unnecessary. In PMA, storing information means encoding it as a mathematical transformation that produces the data when applied to a standardized canonical input; reading means applying the transformation; and computing means composing transformations. This inversion of the conventional von Neumann paradigm yields five emergent architectural properties—structural auditability, transparent reasoning, enforced constraints, tamper evidence, and reversibility—that collectively enable verifiable computation: systems that can mathematically verify the integrity and correctness of their own reasoning chains. We provide a complete mathematical specification of PMA over Galois fields GF(2k) with roundtrip exactness guarantees, constructive algorithms for both invertible and non-invertible encoding modes, and a reference permutation-based embodiment with explicit bit-level storage formats. We analyze thermodynamic properties under reversible logic implementation, demonstrating that PMA operations on adiabatic substrates can approach within 10× of the Landauer limit at the localnode level. We then present the integration architecture for PMA with artificial general intelligence (AGI) safety frameworks, showing how transformation-based reasoning enables safety constraints that are structural rather than advisory—creating systems where unsafe behavior is computationally undefined rather than merely prohibited. We discuss applications to financial auditing, medical AI verification, and autonomous systems governance, and compare PMA's approach to verifiable computation with existing paradigms including blockchain, zero-knowledge proofs, and mechanistic interpretability.
• DeFi stablecoin yields track FFR/SOFR, but with a distinct T+3 structural lag. • A settlement-friction framework links fiat rails to the T+3 transmission lag. • The lag is universal for both compliant USDC and offshore, unregulated USDT. • Basis regressions reveal a predictable settlement wedge after policy moves. • Robust tests rule out protocol outliers, macro trends, and weekend artifacts. Decentralized Finance (DeFi) stablecoin markets increasingly function as a shadow overnight dollar system, yet the speed at which U.S. monetary policy transmits to on-chain yields remains unclear. Focusing on the recent “High-for-Long” regime (2023–2025), I study this pass-through using daily Aave V3 deposit rates for USDC and USDT. Guided by a simple conceptual framework of settlement frictions and arbitrage constraints, I estimate an ordered VAR that controls for equity- and crypto-market cycles. The results show that DeFi yields are tightly anchored to the Federal Funds Rate (and, in robustness, SOFR), challenging the “crypto-decoupling” narrative. However, transmission exhibits a distinct T+3 structural latency, universal across both compliant USDC and unregulated USDT, indicating an infrastructural, systemic friction rather than issuer-specific constraints. Robustness tests, alternative-explanations analysis, and quantity-based mechanism checks rule out protocol outliers, broader macro trends, and weekend artifacts, supporting an interpretation based on delayed settlement and execution across fiat rails. Complementary basis regressions provide a direct pricing implication: the on/off-chain spread exhibits a significant, predictable wedge during the settlement window that dissipates thereafter. The findings imply that despite algorithmic immediacy, DeFi remains constrained by fiat infrastructure, and that improving on-chain capital efficiency may require modernizing payment rails alongside issuer-focused regulation.